© 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. 17-GEMMASCOPE-2-RES-16K
    7. 3051
    Prev
    Next
    INDEX
    Explanations

    model

    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_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
    let
    0.77
     let
    0.73
    Let
    0.73
    )\$(
    0.72
    \},
    0.70
     Let
    0.69
    [,
    0.69
    [
    0.68
     at
    0.67
     अशा
    0.67
    POSITIVE LOGITS
     bac
    0.79
     bahagia
    0.69
     ready
    0.68
     doskona
    0.66
     felicidad
    0.66
     dices
    0.65
     good
    0.65
     meget
    0.64
     miserable
    0.64
     `>=
    0.63
    Activations Density 0.075%

    No Known Activations