© 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. 146263
    Prev
    Next
    INDEX
    Explanations

    and Dragons

    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
     ذہن
    0.75
     Aad
    0.71
    .$(
    0.70
     اک
    0.68
    ſſ
    0.68
     nodig
    0.67
     Grub
    0.67
    zunehmen
    0.67
    が必要です
    0.65
     akong
    0.65
    POSITIVE LOGITS
     kull
    0.69
    bage
    0.69
    토
    0.68
    garia
    0.67
     αποκ
    0.66
     neither
    0.65
    每一次
    0.64
    每次
    0.64
    ORDIN
    0.64
    භාව
    0.64
    Activations Density 0.001%

    No Known Activations