© 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. 111035
    Prev
    Next
    INDEX
    Explanations

    prior art, United States, public access, desk, century

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

    The neuron strongly lights up on uncommon, content-bearing words (i.e. low-frequency, domain-specific tokens) rather than on common function words.

    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
     you
    -1.63
    鹮
    -1.44
    okość
    -1.31
    Fig
    -1.28
    estão
    -1.24
    appspot
    -1.23
    cjonal
    -1.20
     pengunjung
    -1.20
     It
    -1.19
    6
    -1.19
    POSITIVE LOGITS
    
    1.49
    ⛦
    1.41
     vieles
    1.33
     tacón
    1.33
    绛
    1.31
     servis
    1.27
     navide
    1.27
    änemark
    1.25
     wundersch
    1.22
    焢
    1.21
    Activations Density 0.702%

    No Known Activations