© 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. 5454
    Prev
    Next
    INDEX
    Explanations

    basic needs, principles, education

    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
    Various
    1.09
    or
    1.04
    entire
    1.02
    Specifically
    1.01
    ת
    1.01
    Seamless
    0.99
    Exclusive
    0.98
    e
    0.97
    Agu
    0.97
    Assistant
    0.96
    POSITIVE LOGITS
     tenets
    1.67
     necessities
    1.57
     premise
    1.44
     principles
    1.29
    的には
    1.28
     instincts
    1.28
     Instinct
    1.23
     multicellular
    1.17
     fundamentals
    1.15
    DBObject
    1.13
    Activations Density 0.180%

    No Known Activations