© 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. 16-GEMMASCOPE-2-RES-262K
    7. 19953
    Prev
    Next
    INDEX
    Explanations

    champagne healthy, socialists, wishes, spray

    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_16_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
    м
    0.75
    skiej
    0.75
    z
    0.75
     چھوٹے
    0.75
    звичай
    0.74
    
    0.73
    iwers
    0.72
    ле
    0.71
    ști
    0.70
     সময়ে
    0.70
    POSITIVE LOGITS
    I
    1.26
     is
    0.88
     was
    0.88
    ;
    0.81
     to
    0.80
     you
    0.80
    大
    0.80
    ↵↵
    0.79
    ח
    0.75
    in
    0.75
    Activations Density 0.001%

    No Known Activations