© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5527
    Prev
    Next
    INDEX
    Explanations

    not fixed

    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_22_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
     પા
    0.73
     IPO
    0.65
     /=
    0.64
     interpolation
    0.64
     例
    0.64
     връ
    0.63
    interpol
    0.63
     spelled
    0.63
     banding
    0.62
     wartime
    0.62
    POSITIVE LOGITS
    皮膚
    0.73
    shore
    0.71
     मिट्टी
    0.70
    使
    0.70
    青山
    0.68
    物は
    0.68
     stronę
    0.68
    descriptors
    0.68
    資
    0.67
    amos
    0.67
    Activations Density 0.001%

    No Known Activations