© 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. 29-GEMMASCOPE-2-RES-262K
    7. 146667
    Prev
    Next
    INDEX
    Explanations

    was involved, driving, observed, patrolling

    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_29_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
     inexperienced
    0.78
     Pi
    0.74
     young
    0.73
     pula
    0.73
    ﻝ
    0.72
     нов
    0.70
     amazed
    0.70
     thought
    0.69
    minent
    0.69
    以為
    0.68
    POSITIVE LOGITS
    ጆ
    0.76
    ضيف
    0.73
    рати
    0.70
    ress
    0.69
     Sidhu
    0.68
    isjon
    0.67
    MenuStrip
    0.65
    ushchev
    0.65
    collation
    0.65
     Salom
    0.64
    Activations Density 0.001%

    No Known Activations