© 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. 146293
    Prev
    Next
    INDEX
    Explanations

    take a cut

    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
     Sess
    0.70
     стен
    0.69
    وسف
    0.68
    chema
    0.66
     কেন
    0.66
    вающие
    0.65
    मानी
    0.64
     為
    0.63
     Movement
    0.61
     переме
    0.61
    POSITIVE LOGITS
    lington
    0.73
    ภาษ
    0.70
     deflation
    0.70
     passare
    0.70
     nikdy
    0.69
     passer
    0.69
     slightest
    0.69
    拱
    0.69
     painted
    0.68
     done
    0.68
    Activations Density 0.001%

    No Known Activations