© 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-65K
    7. 7443
    Prev
    Next
    INDEX
    Explanations

    statements of approval or recommendation

    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_65k_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
    Westinghouse
    0.43
     richiede
    0.42
     Vẽ
    0.41
    kB
    0.40
    Siehe
    0.40
     />);
    0.40
     Betracht
    0.39
     त्यासाठी
    0.39
    ১৬
    0.39
    Youtube
    0.39
    POSITIVE LOGITS
     somm
    0.45
    aryl
    0.44
    :
    0.44
     рецен
    0.43
    }:
    0.42
    ：
    0.42
     Experts
    0.42
     Reviewed
    0.41
     reviewers
    0.41
    ité
    0.40
    Activations Density 0.002%

    No Known Activations