© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49094
    Prev
    Next
    INDEX
    Explanations

    introduction and fields

    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
    montage
    -0.81
     قهوه
    -0.80
    struzioni
    -0.79
    blown
    -0.76
     estilo
    -0.73
    Cement
    -0.73
     bandera
    -0.73
    stine
    -0.72
    nth
    -0.72
    liang
    -0.71
    POSITIVE LOGITS
     analysis
    0.86
     boost
    0.84
     field
    0.84
    Field
    0.83
     conflicts
    0.82
    analyser
    0.81
     analyzed
    0.81
     analyzing
    0.80
     boosts
    0.79
    登録
    0.78
    Activations Density 0.025%

    No Known Activations