© 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. 15-GEMMASCOPE-2-RES-262K
    7. 69590
    Prev
    Next
    INDEX
    Explanations

    apple

    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_15_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
     endIndex
    1.63
    paro
    1.52
    ною
    1.49
    ich
    1.48
     materna
    1.43
    胞
    1.43
    rea
    1.43
    sz
    1.43
    ʰ
    1.41
    nosti
    1.39
    POSITIVE LOGITS
     Cyn
    1.31
     minded
    1.27
     stormy
    1.27
     tying
    1.27
    льти
    1.25
    未必
    1.24
    赌
    1.24
     videom
    1.23
     thoughtful
    1.22
     guarding
    1.21
    Activations Density 0.001%

    No Known Activations