© 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. 22-GEMMASCOPE-RES-131K
    7. 14977
    Prev
    Next
    INDEX
    Explanations

    this and

    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
     its
    -1.30
     even
    -1.29
     Ál
    -1.23
    ƶ
    -1.16
     this
    -1.16
     Ár
    -1.15
     those
    -1.11
     Voraus
    -1.11
     all
    -1.11
     the
    -1.11
    POSITIVE LOGITS
    ,
    1.23
    </em>
    1.16
     Игорь
    1.09
    h
    1.07
    codiles
    1.06
    が
    1.05
    érieur
    1.05
    primarily
    1.02
    所以在
    1.01
    на
    1.00
    Activations Density 0.038%

    No Known Activations