© 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
    2. Gemma-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 1542
    Prev
    Next
    INDEX
    Explanations

    loving housewife

    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
    )):
    1.67
    )\}
    1.54
    または
    1.54
    ).-
    1.54
    可通过
    1.48
    ):
    1.46
    および
    1.43
    OTOS
    1.43
    ⟋
    1.40
     $:
    1.39
    POSITIVE LOGITS
     [
    3.52
     really
    2.93
     thing
    2.76
     guys
    2.73
    [
    2.54
     stuff
    2.51
     kinda
    2.51
    ..."
    2.46
     things
    2.46
    …"
    2.39
    Activations Density 1.059%

    No Known Activations