© 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. 107384
    Prev
    Next
    INDEX
    Explanations

    builder too

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

    common to

    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
     Kit
    0.52
     بچہ
    0.49
     Market
    0.48
     NaN
    0.48
     beserta
    0.48
     KIT
    0.47
     +
    0.46
     pertanto
    0.46
    はその
    0.45
     market
    0.44
    POSITIVE LOGITS
    炀
    0.50
    ෙන්
    0.46
     detractors
    0.46
    ردم
    0.45
    remmo
    0.43
    ías
    0.43
    墨
    0.43
    imidazole
    0.42
    女主
    0.42
    더
    0.42
    Activations Density 0.000%

    No Known Activations