© 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. 1287
    Prev
    Next
    INDEX
    Explanations

    does not constitute advice

    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
     (
    0.81
     pe
    0.56
     ja
    0.56
    ью
    0.52
    ро
    0.51
    ё
    0.51
     small
    0.50
    i
    0.50
    house
    0.50
     dran
    0.50
    POSITIVE LOGITS
    <unused704>
    1.02
     Rv
    1.00
    <unused1127>
    1.00
    <unused645>
    0.99
    <unused448>
    0.98
    <unused994>
    0.98
    fNil
    0.97
    <unused756>
    0.97
    <unused372>
    0.97
     pathophys
    0.97
    Activations Density 0.027%

    No Known Activations