© 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. 5072
    Prev
    Next
    INDEX
    Explanations

    it with

    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
    empuan
    0.75
     rootView
    0.75
    <unused605>
    0.73
     অগ
    0.73
    ocortic
    0.73
    itorios
    0.71
     availed
    0.71
    <unused608>
    0.71
     plenum
    0.71
    胗
    0.70
    POSITIVE LOGITS
     Head
    0.75
    head
    0.74
    Head
    0.69
     head
    0.68
     Copper
    0.60
    urity
    0.59
    HEAD
    0.57
    owie
    0.56
    дер
    0.56
    askar
    0.56
    Activations Density 0.067%

    No Known Activations