© 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. 9013
    Prev
    Next
    INDEX
    Explanations

    authors and specific places

    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
    <unused1015>
    0.49
    <unused1080>
    0.46
    urized
    0.46
    <unused2136>
    0.46
    kannya
    0.45
    <unused1005>
    0.45
    fühl
    0.44
    lcl
    0.44
    ură
    0.44
    ovanja
    0.43
    POSITIVE LOGITS
     To
    0.33
     I
    0.32
     others
    0.32
     Is
    0.32
     It
    0.30
     umbrella
    0.30
     linguistic
    0.30
     If
    0.30
     ad
    0.29
     But
    0.29
    Activations Density 0.000%

    No Known Activations