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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 2252
    Prev
    Next
    INDEX
    Explanations

    describing smart technology

    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
     glory
    1.09
     pillars
    0.97
    শ
    0.97
    向
    0.96
    瑟
    0.93
    fläche
    0.92
     Glory
    0.91
    Ω
    0.91
    ající
    0.91
     휘
    0.89
    POSITIVE LOGITS
    erweise
    1.38
    dumb
    1.26
     Enough
    1.19
     minds
    1.14
     acumen
    1.14
    ফোন
    1.11
    netic
    1.10
     quotient
    1.07
    बूझ
    1.07
     savvy
    1.06
    Activations Density 0.074%

    No Known Activations