© 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
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 5136
    Prev
    Next
    INDEX
    Explanations

    SQL database commands

    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
     (
    1.04
     filled
    1.04
     the
    0.95
     your
    0.94
     a
    0.90
     Y
    0.88
     as
    0.87
     case
    0.86
     broad
    0.86
     American
    0.84
    POSITIVE LOGITS
    MySQL
    1.26
    mysql
    1.13
    MYSQL
    1.10
    Características
    1.05
    Điều
    1.04
     */;
    1.04
    Backup
    1.04
    Benzoimidazol
    1.03
     setToDefault
    1.01
    Perfil
    1.01
    Activations Density 0.003%

    No Known Activations