© 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. 5656
    Prev
    Next
    INDEX
    Explanations

    python code blocks

    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
     bodies
    0.60
    옐
    0.59
    ～。
    0.58
     aus
    0.56
    চনার
    0.55
     gin
    0.54
    inely
    0.54
     สิ
    0.54
     dehyd
    0.53
    itative
    0.53
    POSITIVE LOGITS
    टू
    0.79
    Quality
    0.76
    мента
    0.71
     Detail
    0.71
    ?";
    0.71
    طلا
    0.70
     trajetória
    0.70
    traverse
    0.69
    Trajectory
    0.68
    ictive
    0.68
    Activations Density 0.048%

    No Known Activations