© 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. 71704
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     at
    -1.91
     our
    -1.84
     in
    -1.81
     we
    -1.66
     before
    -1.63
     when
    -1.62
     or
    -1.53
     not
    -1.51
     with
    -1.50
     after
    -1.50
    POSITIVE LOGITS
     diriger
    1.64
     alcune
    1.55
     certaines
    1.47
    neous
    1.43
     alcuni
    1.43
    などを
    1.42
    ඍ
    1.41
     BEING
    1.38
     momentan
    1.38
     ..........
    1.38
    Activations Density 0.053%

    No Known Activations