© 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. 40-GEMMASCOPE-2-RES-262K
    7. 11889
    Prev
    Next
    INDEX
    Explanations

    section marker "I."

    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_40_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
    ֗
    0.36
    enediamine
    0.34
    ]!='
    0.34
     núcle
    0.34
     précie
    0.33
    )：
    0.33
    šev
    0.33
     reinsurance
    0.33
    ّٰ
    0.33
     bén
    0.32
    POSITIVE LOGITS
    .,
    0.32
     अजय
    0.32
     slammed
    0.32
    Ring
    0.31
     Checklist
    0.31
    ैम
    0.31
    "}
    0.31
     checklist
    0.30
    Baby
    0.30
    rawn
    0.30
    Activations Density 0.007%

    No Known Activations