© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1695
    Prev
    Next
    INDEX
    Explanations

    delve deeper into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     hatchback
    0.94
     monstros
    0.93
    ப்புகள்
    0.91
     endeavors
    0.90
    ❦
    0.90
     lím
    0.89
     🥰
    0.89
    <unused2138>
    0.89
    ப்புகளை
    0.89
    সঙ্ঘ
    0.88
    POSITIVE LOGITS
     into
    0.99
     deep
    0.95
     depth
    0.93
     deepest
    0.92
    into
    0.92
    Depth
    0.90
    深度
    0.90
     Depth
    0.86
     deeper
    0.85
    depth
    0.84
    Activations Density 0.109%

    No Known Activations