© 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. 15886
    Prev
    Next
    INDEX
    Explanations

    multi-day events

    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
    手間
    0.49
    ダメージ
    0.48
    歴
    0.47
     Commentaires
    0.46
     luminoso
    0.46
     Retry
    0.46
     জীবনী
    0.45
    不太
    0.45
     Residences
    0.44
     बहनों
    0.44
    POSITIVE LOGITS
     feats
    0.48
    ष्टि
    0.45
    pani
    0.45
    kst
    0.44
    ɮ
    0.44
    ANI
    0.43
    grant
    0.43
    kult
    0.43
    desc
    0.43
    bari
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.