© 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. 11910
    Prev
    Next
    INDEX
    Explanations

    history or current state

    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
     pé
    1.18
    Ύ
    1.14
    schl
    1.03
    Rés
    1.02
    Wan
    1.02
     intelligent
    1.01
    othed
    1.01
    मुखी
    1.00
    สถาน
    0.99
     prec
    0.99
    POSITIVE LOGITS
    溯
    1.07
    ⃞
    1.06
    态
    1.04
    目录下
    1.03
    त
    0.99
     spain
    0.98
    credibly
    0.98
     இருந்து
    0.97
    体の
    0.97
    体的
    0.96
    Activations Density 0.000%

    No Known Activations