© 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. 64067
    Prev
    Next
    INDEX
    Explanations

    introduction section heading

    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
     even
    -1.06
     spise
    -0.98
     on
    -0.95
     t
    -0.93
     old
    -0.92
     impeccable
    -0.90
     at
    -0.89
     \&
    -0.87
     one
    -0.86
    ったのは
    -0.85
    POSITIVE LOGITS
    \
    1.63
     bisherigen
    1.13
    eſt
    1.12
    開始
    1.08
     Fähigkeit
    1.06
     definição
    1.05
    eſ
    1.03
    わたしは
    1.03
    再说
    1.02
    Literat
    1.02
    Activations Density 0.030%

    No Known Activations