© 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. 47604
    Prev
    Next
    INDEX
    Explanations

    on location or time

    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
    や
    -0.89
    ateri
    -0.85
    edificio
    -0.82
     ساختمان
    -0.82
    <bos>
    -0.78
    队伍
    -0.76
    edere
    -0.76
     nơi
    -0.74
    ormais
    -0.73
    lijken
    -0.73
    POSITIVE LOGITS
     behalf
    0.98
    も良い
    0.97
     basis
    0.91
    心头
    0.88
     this
    0.83
    夕方
    0.82
    anthene
    0.82
     which
    0.82
    recrow
    0.81
    ostro
    0.81
    Activations Density 0.003%

    No Known Activations