© 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. 79185
    Prev
    Next
    INDEX
    Explanations

    and numbers

    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
     ſmall
    -1.48
    傒
    -1.45
    𓁹
    -1.42
    oneof
    -1.41
     profesora
    -1.34
    mittelt
    -1.29
     lã
    -1.27
    歺
    -1.26
    骉
    -1.26
     ſou
    -1.26
    POSITIVE LOGITS
     had
    1.67
     also
    1.63
     was
    1.59
     then
    1.53
     received
    1.43
     became
    1.41
     could
    1.38
     took
    1.38
     now
    1.38
     will
    1.38
    Activations Density 0.022%

    No Known Activations