© 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. 18083
    Prev
    Next
    INDEX
    Explanations

    points and coordinates

    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
    㜌
    0.53
    SetStr
    0.48
     الواحده
    0.48
    StoredKeys
    0.47
     сериа
    0.46
    价值观
    0.45
    大街
    0.44
     vaisse
    0.42
     asociaciones
    0.42
    大赛
    0.42
    POSITIVE LOGITS
     points
    0.86
     B
    0.84
     point
    0.82
     A
    0.79
     midpoint
    0.75
     O
    0.71
     Point
    0.70
     P
    0.68
    points
    0.66
    O
    0.64
    Activations Density 0.012%

    No Known Activations