© 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. 393
    Prev
    Next
    INDEX
    Explanations

    Okay,

    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
     otras
    0.80
     тво
    0.80
    愿
    0.77
     please
    0.73
    また
    0.72
     diaria
    0.71
    bump
    0.71
    请
    0.71
     wouldn
    0.70
     útiles
    0.69
    POSITIVE LOGITS
    ERTY
    0.90
     prestación
    0.88
    ҝ
    0.86
     Gori
    0.84
    ılabilir
    0.83
    صول
    0.82
    ங்கிணை
    0.81
     Srivastava
    0.80
    .}$
    0.80
    erent
    0.80
    Activations Density 0.275%

    No Known Activations