© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76730
    Prev
    Next
    INDEX
    Explanations

    avoid or where

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    อ
    0.59
    ⸩
    0.49
    音
    0.48
     любви
    0.46
     ufficiale
    0.46
    Coluna
    0.46
     인증
    0.46
    月
    0.45
    リアル
    0.45
    тпу
    0.45
    POSITIVE LOGITS
     Why
    0.46
     kenapa
    0.44
     gardeners
    0.43
     Recipe
    0.43
    amaged
    0.43
     Phosphorus
    0.43
    ipak
    0.42
     Dysfunction
    0.42
     Chadwick
    0.42
     Dune
    0.42
    Activations Density 0.015%

    No Known Activations