© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 162
    Prev
    Next
    INDEX
    Explanations

    price range and turkish content

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

    The neuron fires on numeric tokens and number literals (e.g. digits, percentages, decimal values, IP octets, hex-digit sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     will
    -1.52
     what
    -1.50
     one
    -1.48
     these
    -1.44
    From
    -1.42
     this
    -1.38
     even
    -1.38
     how
    -1.38
    T
    -1.36
    Even
    -1.34
    POSITIVE LOGITS
     solides
    1.38
     benzin
    1.36
     türk
    1.30
     poiv
    1.30
    Gön
    1.30
     douze
    1.29
    Dres
    1.28
     dichter
    1.28
    🫁
    1.27
     gier
    1.26
    Activations Density 0.001%

    No Known Activations