© 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. 53-GEMMASCOPE-2-RES-262K
    7. 66491
    Prev
    Next
    INDEX
    Explanations

    FOR OFFICIAL USE

    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_53_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
     Quasi
    0.47
     كتب
    0.44
    ätzung
    0.41
     Beta
    0.41
     పంట
    0.40
    腃
    0.40
     Não
    0.40
     ማን
    0.40
    ⒉
    0.40
     ALPINE
    0.39
    POSITIVE LOGITS
     spills
    0.40
    worlds
    0.40
    S
    0.39
    weeks
    0.37
    off
    0.36
    meg
    0.36
     weaker
    0.36
     heed
    0.36
    ame
    0.35
    attach
    0.35
    Activations Density 0.000%

    No Known Activations