© 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. 55896
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
    Although
    -1.08
    Despite
    -1.00
    Ayrıca
    -0.99
    }{*}{}
    -0.97
    There
    -0.97
    логических
    -0.96
    Since
    -0.94
    Many
    -0.93
    我们的
    -0.93
    These
    -0.93
    POSITIVE LOGITS
     stutter
    0.93
     grandiose
    0.86
    られて
    0.85
     vectoriales
    0.84
     निम्न
    0.83
    是用
    0.83
     instead
    0.82
     recreated
    0.82
     salv
    0.81
     consec
    0.81
    Activations Density 0.000%

    No Known Activations