© 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. 136017
    Prev
    Next
    INDEX
    Explanations

    comparing and contrasting ideas

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

    Rewards, resources, period, everything, trace

    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
    ﮐ
    0.52
    ୭
    0.49
     sağlık
    0.46
    ﺛ
    0.46
    ୩
    0.45
     richiesta
    0.45
    │
    0.44
    \|\
    0.44
     adot
    0.44
    を採用
    0.44
    POSITIVE LOGITS
     Trento
    0.49
    يرين
    0.47
     Commonly
    0.46
     Collo
    0.45
     Emperors
    0.44
    atology
    0.44
    commonly
    0.44
     Bamberg
    0.44
    NewUrl
    0.43
    enze
    0.43
    Activations Density 0.000%

    No Known Activations