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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59797
    Prev
    Next
    INDEX
    Explanations

    code keywords

    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
     those
    -1.25
     any
    -1.13
     even
    -1.13
     several
    -1.13
     what
    -1.09
    そして
    -1.02
     especially
    -1.02
     not
    -1.00
    mą
    -0.98
     sejumlah
    -0.98
    POSITIVE LOGITS
     WEST
    1.08
     portugués
    1.05
     thì
    1.04
    ;//
    1.04
    ;
    1.02
    </b>
    1.01
     gekenn
    0.97
    ÍSTICAS
    0.96
     alho
    0.95
    ÍT
    0.93
    Activations Density 0.004%

    No Known Activations