© 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. 4292
    Prev
    Next
    INDEX
    Explanations

    age height weight

    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
    اشت
    0.89
    лни
    0.87
    பல
    0.84
     сё
    0.83
     głos
    0.83
    ця
    0.81
    腑
    0.80
    сы
    0.79
     apoyar
    0.79
     mash
    0.79
    POSITIVE LOGITS
    र्वेद
    1.16
     exced
    1.08
    keepers
    1.00
     determinations
    1.00
    keeper
    0.99
    wise
    0.96
     گیری
    0.96
     limite
    0.94
    ways
    0.93
    metry
    0.93
    Activations Density 0.254%

    No Known Activations