© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65801
    Prev
    Next
    INDEX
    Explanations

    cold Bass Bush alb Bas Bia B

    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
     contando
    -0.77
    を
    -0.76
    バランス
    -0.76
     Phú
    -0.75
    aop
    -0.75
     الجمه
    -0.73
     faisait
    -0.72
    ですが
    -0.70
     langsung
    -0.70
    راهيم
    -0.69
    POSITIVE LOGITS
    ようになる
    0.83
    Cold
    0.83
    licazione
    0.82
     COLD
    0.82
     prospectus
    0.81
    encias
    0.79
     Remains
    0.77
    cold
    0.77
    んですね
    0.76
    yszer
    0.75
    Activations Density 0.004%

    No Known Activations