© 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. 69773
    Prev
    Next
    INDEX
    Explanations

    sea versions inspiring aging

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

    predictive model components

    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
     soie
    0.45
    強度
    0.44
    ۹
    0.44
    دت
    0.43
     virtuales
    0.43
    雓
    0.43
    iem
    0.43
    krb
    0.43
     מכ
    0.42
    箴
    0.42
    POSITIVE LOGITS
     clap
    0.46
    Flights
    0.45
     Hyde
    0.44
     Chip
    0.40
     batal
    0.40
    Chip
    0.39
     Battles
    0.39
     mirac
    0.39
     খায়
    0.39
     unload
    0.39
    Activations Density 0.000%

    No Known Activations