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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 452
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’
    1.47
     is
    1.44
     has
    1.41
     was
    1.34
    .
    1.32
     of
    1.31
    We
    1.31
    -
    1.31
     have
    1.31
     We
    1.30
    POSITIVE LOGITS
    <unused912>
    1.57
     lineColorSpace
    1.56
    lwjglVersion
    1.53
    nBitCount
    1.53
     givenChar
    1.53
    LOTREntity
    1.52
    spiderX
    1.51
    lbrakk
    1.51
    MathMarks
    1.51
    BFAppLink
    1.50
    Activations Density 4.859%

    No Known Activations