© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 982
    Prev
    Next
    INDEX
    Explanations

    As followed by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    ن
    1.29
    et
    1.18
    タ
    1.06
    ように
    1.04
    los
    0.99
    emph
    0.98
    ний
    0.95
    fabs
    0.93
    e
    0.93
    tic
    0.93
    POSITIVE LOGITS
     evidenced
    1.57
     opposed
    1.49
     follows
    1.47
    sembling
    1.44
    sembled
    1.43
    ymptotic
    1.40
    pekte
    1.39
    pergillus
    1.27
    ymmet
    1.25
     oppose
    1.25
    Activations Density 0.062%

    No Known Activations