© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14136
    Prev
    Next
    INDEX
    Explanations

    finding dimensions or positions

    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_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
    流
    1.21
     സുമിത്ര
    1.20
     Trades
    1.14
    േക്ക്
    1.12
     Job
    1.08
    他说
    1.08
    半
    1.07
    𒀝
    1.06
     Repe
    1.06
     Swap
    1.06
    POSITIVE LOGITS
     в
    1.06
    ,
    1.06
     (
    1.00
    ించిన
    0.95
     in
    0.95
     ใน
    0.90
    _
    0.88
     из
    0.83
    orthogonal
    0.81
    as
    0.80
    Activations Density 0.013%

    No Known Activations