© 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-262K
    4. 1655
    Prev
    Next
    INDEX
    Explanations

    code identifiers and syntax

    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_262k_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
     cavities
    0.61
     primal
    0.56
     onerous
    0.56
     tribulations
    0.56
     extremal
    0.55
     obce
    0.55
    එ
    0.54
     incul
    0.54
     escenarios
    0.54
     irrational
    0.54
    POSITIVE LOGITS
    _
    0.95
    と
    0.75
     యొక్క
    0.75
     को
    0.75
    中的
    0.74
    ને
    0.73
    に対して
    0.73
    の
    0.72
    __
    0.72
     کے
    0.71
    Activations Density 0.322%

    No Known Activations