© 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. 38776
    Prev
    Next
    INDEX
    Explanations

    Two distinctMore RedMore waterFeet shoulder-width

    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
    ص
    0.54
     annunci
    0.47
    )]=
    0.47
    नव
    0.46
     οικονομ
    0.45
    ']))->
    0.45
     enteral
    0.44
    ))=\
    0.44
     økonom
    0.43
     ekonom
    0.43
    POSITIVE LOGITS
    rained
    0.53
    cur
    0.52
    err
    0.48
    list
    0.47
    rive
    0.46
     curving
    0.46
    slider
    0.46
     decept
    0.45
     disagreement
    0.45
    running
    0.45
    Activations Density 0.007%

    No Known Activations