© 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. 75186
    Prev
    Next
    INDEX
    Explanations

    live among

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

    used to mean

    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
    গা
    0.50
    ){}
    0.47
     precious
    0.44
     pungent
    0.42
    कहां
    0.42
     Mystic
    0.42
    getC
    0.42
     Rocky
    0.41
    திரு
    0.41
    minimize
    0.41
    POSITIVE LOGITS
    رو
    0.47
    ături
    0.45
    OEt
    0.44
     अमल
    0.43
     椅
    0.42
     probleme
    0.42
    enbach
    0.42
     pruž
    0.42
     Суриков
    0.42
    ＮＡ
    0.42
    Activations Density 0.000%

    No Known Activations