© 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. 31056
    Prev
    Next
    INDEX
    Explanations

    level cap and specific levels

    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
    inguish
    -0.83
     narrowed
    -0.81
     narrower
    -0.79
    oléon
    -0.78
    MPN
    -0.78
     注册
    -0.75
    estanden
    -0.73
    ℡
    -0.71
     privée
    -0.71
    vb
    -0.71
    POSITIVE LOGITS
    isRequired
    0.95
    requirement
    0.90
     requirement
    0.90
     requer
    0.89
    req
    0.83
     Requirement
    0.82
    _{*}
    0.80
     req
    0.79
    requirements
    0.79
    verre
    0.77
    Activations Density 0.014%

    No Known Activations