© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 118930
    Prev
    Next
    INDEX
    Explanations

    China Human, Treatment of, MRI-derived

    np_acts-logits-general · gemini-2.5-flash-lite

    special characters and abbreviations in technical or scientific text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is acting as a crude document-position detector, firing strongest on tokens near the start of the text and gradually decaying as you go further down.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    шип
    -1.52
    ikusbot
    -1.45
     "
    -1.44
    itectura
    -1.41
                
    -1.38
    ッフェ
    -1.38
     it
    -1.36
            
    -1.35
    "'
    -1.35
     '"
    -1.34
    POSITIVE LOGITS
     getrock
    1.37
     видит
    1.32
     vaisselle
    1.29
     Früchte
    1.28
    SEMICOLON
    1.27
     sixth
    1.27
     помню
    1.25
    Ruju
    1.25
    しかし
    1.24
    خوری
    1.22
    Activations Density 0.000%

    No Known Activations