© 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. 2289
    Prev
    Next
    INDEX
    Explanations

    custom photo items

    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
    顐
    0.39
    ifiées
    0.38
    advised
    0.38
    ifiée
    0.38
    otene
    0.38
     swearing
    0.37
     ವಿರು
    0.37
    anjut
    0.36
    ្សែ
    0.36
    beelding
    0.36
    POSITIVE LOGITS
     J
    0.43
    ↵↵
    0.42
     T
    0.41
     This
    0.41
     S
    0.40
     Toyota
    0.39
    S
    0.39
     P
    0.38
     GCSE
    0.38
     Custom
    0.38
    Activations Density 0.002%

    No Known Activations