Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 778
    Prev
    Next
    INDEX
    Explanations

    Google search and perspectives

    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
    スケジュール
    1.64
    \|
    1.51
    تك
    1.43
    &-
    1.41
     reckons
    1.40
     (£
    1.37
    ption
    1.36
    が
    1.35
    *
    1.34
    中の
    1.29
    POSITIVE LOGITS
     opposed
    2.83
     well
    2.74
    ynchronously
    2.73
    rinsic
    2.65
    otrop
    2.42
    well
    2.38
    sembled
    2.36
    thaus
    2.34
    sembles
    2.33
    amblea
    2.31
    Activations Density 0.223%

    No Known Activations