© 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. 15-GEMMASCOPE-2-RES-262K
    4. 69904
    Prev
    Next
    INDEX
    Explanations

    much faster

    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
    才知道
    1.92
    她说
    1.79
    魇
    1.72
     Wnd
    1.69
    חנו
    1.69
    やっと
    1.67
    他說
    1.67
    odings
    1.64
     competitors
    1.64
    在這裡
    1.63
    POSITIVE LOGITS
    alkyl
    1.39
    т
    1.36
     või
    1.35
    𝗮
    1.34
    ault
    1.33
     kHz
    1.32
    unsubscribe
    1.30
    etary
    1.27
    QUENCY
    1.26
     Rivière
    1.24
    Activations Density 0.000%

    No Known Activations