© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1518
    Prev
    Next
    INDEX
    Explanations

    vote, languages, person

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_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
     craze
    1.05
    ृत
    1.03
     subclass
    1.01
    (
    0.99
     flash
    0.98
    -
    0.98
     downside
    0.96
     gusto
    0.95
     অপরের
    0.94
    Research
    0.94
    POSITIVE LOGITS
    ultima
    1.19
    籬
    1.04
     últimos
    1.04
    <unused1033>
    0.99
    äfte
    0.98
    şiv
    0.98
     Resume
    0.98
    علن
    0.97
     Obligations
    0.96
     शीट
    0.95
    Activations Density 0.000%

    No Known Activations