© 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. 97830
    Prev
    Next
    INDEX
    Explanations

    above copyright

    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
    gering
    -0.86
    spots
    -0.86
     Maximilian
    -0.84
    雰囲気が
    -0.84
    ifying
    -0.83
     dopiero
    -0.82
    optionalTypeArgs
    -0.82
     révélé
    -0.82
    ALLOWED
    -0.81
    日が
    -0.79
    POSITIVE LOGITS
     from
    0.98
     of
    0.85
     héro
    0.75
     conservatism
    0.74
     outages
    0.74
    вез
    0.74
     ifrån
    0.73
    Hymen
    0.73
    υμ
    0.72
     nerf
    0.71
    Activations Density 0.001%

    No Known Activations