© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 13419
    Prev
    Next
    INDEX
    Explanations

    action, action plan, action item, action verbs

    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
    ek
    1.19
    я
    1.19
    i
    1.09
    𝑆
    1.07
    𝘈
    1.07
    𝑇
    1.06
    ял
    1.05
     psoriasis
    1.05
    言
    1.04
    गण
    1.01
    POSITIVE LOGITS
    nable
    1.40
    ный
    1.16
    Taken
    1.06
    er
    1.04
    naires
    1.03
    ഹ്ലാദ
    0.97
    ার
    0.96
    ഷി
    0.96
    ные
    0.95
    prendre
    0.95
    Activations Density 0.037%

    No Known Activations