© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 62889
    Prev
    Next
    INDEX
    Explanations

    legal, technical, and content terms

    np_acts-logits-general · gemini-2.5-flash-lite

    models and solutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.49
    arne
    0.48
    refer
    0.48
    we
    0.46
    .
    0.46
    च्
    0.46
    u
    0.45
    ler
    0.43
    uć
    0.43
    unting
    0.42
    POSITIVE LOGITS
    <unused37>
    0.58
     Рим
    0.50
    স
    0.49
     enduro
    0.48
    вшиеся
    0.47
     entrevista
    0.47
     выпла
    0.47
    щины
    0.47
     bevy
    0.47
    㢼
    0.47
    Activations Density 0.000%

    No Known Activations