© 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. 131291
    Prev
    Next
    INDEX
    Explanations

    change, illiquidity, you never, icebreaker, lens surface

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

    Graph API

    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
     cultivate
    0.48
    щи
    0.47
     жить
    0.45
     ['(?
    0.44
     хватает
    0.44
    বুদ্ধ
    0.43
     сезо
    0.42
     cultivator
    0.42
     grind
    0.41
     buddhav
    0.41
    POSITIVE LOGITS
    員
    0.45
    浜
    0.45
    ロッ
    0.43
    ﾁ
    0.43
    लेट
    0.42
    Ｕ
    0.42
     मटेरियल
    0.42
    અમ
    0.41
    ソン
    0.41
    ഊ
    0.41
    Activations Density 0.000%

    No Known Activations