© 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-262K
    7. 12350
    Prev
    Next
    INDEX
    Explanations

    clear function and docstring explanations

    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
     inm
    0.99
    ాన్ని
    0.96
    ษา
    0.95
     кло
    0.92
    aan
    0.91
    oine
    0.88
     doe
    0.88
    એ
    0.87
    ్రీ
    0.87
     lecz
    0.87
    POSITIVE LOGITS
     ràng
    1.99
    เจน
    1.61
     delineation
    1.59
     demarcation
    1.43
     delineated
    1.43
     indication
    1.42
     demarc
    1.40
     indications
    1.39
     distinction
    1.37
     concise
    1.34
    Activations Density 0.069%

    No Known Activations