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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 1035
    Prev
    Next
    INDEX
    Explanations

    code and markdown elements

    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_65k_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
     ẞ
    0.86
    ֑
    0.79
    ...");
    0.70
    ...")
    0.65
    }\|_{
    0.64
    ...</
    0.59
    ...');
    0.58
    ...",
    0.58
    ">{
    0.58
    .},
    0.58
    POSITIVE LOGITS
    ↵↵
    2.73
    ↵↵↵
    1.77
    ↵↵↵↵
    1.60
    ↵↵↵↵↵
    1.36
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.10
    ↵↵↵↵↵↵↵↵
    1.07
    ↵↵↵↵↵↵
    1.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.04
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.02
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.01
    Activations Density 3.941%

    No Known Activations