© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 72368
    Prev
    Next
    INDEX
    Explanations

    method startup calls

    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
    -1.62
     not
    -1.41
     their
    -1.25
     in
    -1.18
    はその
    -1.09
     by
    -1.09
     for
    -1.06
    هاز
    -1.05
     now
    -1.02
     three
    -1.00
    POSITIVE LOGITS
     refroid
    1.12
     рассказала
    1.07
     occuper
    1.04
     commencer
    1.02
     coû
    1.00
     dépenses
    0.99
     появится
    0.95
     engend
    0.93
    ようになります
    0.93
     rassemb
    0.93
    Activations Density 0.003%

    No Known Activations