© 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. 34-GEMMASCOPE-RES-131K
    7. 107129
    Prev
    Next
    INDEX
    Explanations

    software license and fetch operations

    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
     šo
    -0.79
     прямо
    -0.75
     ドラマ
    -0.73
    ኑ
    -0.69
    зин
    -0.67
     enfermed
    -0.66
    UESDAY
    -0.66
    唖
    -0.65
    yao
    -0.65
    alugar
    -0.65
    POSITIVE LOGITS
    젖
    0.72
    wies
    0.68
    mlx
    0.68
     Agents
    0.66
     __('
    0.66
    ônica
    0.65
    postValue
    0.65
    Compat
    0.65
    Traversal
    0.65
    utare
    0.64
    Activations Density 0.060%

    No Known Activations