© 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. 22-GEMMASCOPE-RES-131K
    7. 65375
    Prev
    Next
    INDEX
    Explanations

    legal clauses and policies

    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_22/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
    夕食
    -0.88
    気軽
    -0.85
     referring
    -0.79
     克
    -0.77
    SeekBar
    -0.75
     also
    -0.75
     ännu
    -0.75
    ed
    -0.75
     Strepto
    -0.74
     EAT
    -0.74
    POSITIVE LOGITS
    Semua
    1.02
    unknownFields
    0.99
    ־ה
    0.97
     hodin
    0.97
     ſuch
    0.93
    juries
    0.93
    ทุก
    0.92
     decorativos
    0.89
    everything
    0.88
    هره
    0.88
    Activations Density 0.151%

    No Known Activations