© 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. 3527
    Prev
    Next
    INDEX
    Explanations

    specific object or concept

    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
     douze
    0.51
     ennemis
    0.49
    コンピュー
    0.48
    髑
    0.48
     감소
    0.48
     salaire
    0.46
     publique
    0.46
    エレ
    0.46
    ین
    0.45
    テー
    0.45
    POSITIVE LOGITS
    pt
    0.53
    form
    0.51
     Inspect
    0.48
    etan
    0.47
    Kur
    0.46
     Kur
    0.45
    kur
    0.45
    ả
    0.44
    Inspect
    0.44
     PT
    0.43
    Activations Density 0.000%

    No Known Activations