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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107902
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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_34/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
     on
    -1.23
     if
    -1.04
     all
    -1.01
     as
    -1.00
     markedly
    -0.96
     at
    -0.96
     out
    -0.94
     or
    -0.93
     with
    -0.89
     full
    -0.89
    POSITIVE LOGITS
     molti
    1.41
     vielen
    1.22
     molte
    1.06
     många
    1.05
    mitteln
    1.03
     muitos
    1.02
     inability
    1.00
     MANY
    0.97
    Invo
    0.97
     viele
    0.96
    Activations Density 0.003%

    No Known Activations