© 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. 41985
    Prev
    Next
    INDEX
    Explanations

    Percentage and reports

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

    understanding percentages

    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
     vertebr
    0.47
     erect
    0.45
     социа
    0.45
     randomize
    0.44
    ２
    0.44
     optimale
    0.44
    frac
    0.43
     metade
    0.43
     uns
    0.43
     representantes
    0.42
    POSITIVE LOGITS
    igrants
    0.45
    辅
    0.43
    谈判
    0.43
     পথ
    0.43
    鹌
    0.43
    už
    0.42
    Maurice
    0.42
    ICH
    0.42
    ICI
    0.42
    Princess
    0.42
    Activations Density 0.000%

    No Known Activations