© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1653
    Prev
    Next
    INDEX
    Explanations

    conversational turn markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    ,
    2.09
    /
    1.90
    .
    1.86
     (
    1.82
    ...
    1.77
    …
    1.71
    系列
    1.69
    系列的
    1.62
    ／
    1.55
    '
    1.48
    POSITIVE LOGITS
     namely
    2.21
    это
    1.98
     absorb
    1.98
     absorbing
    1.97
     perceiving
    1.94
     reclaiming
    1.92
     obeying
    1.88
    absorbing
    1.85
    abhavo
    1.84
    rinsic
    1.84
    Activations Density 0.301%

    No Known Activations