© 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. 146228
    Prev
    Next
    INDEX
    Explanations

    programmatic syntax

    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
    ঁর
    0.75
     আদর
    0.74
     kesempatan
    0.70
    })`;
    0.70
    મારા
    0.69
     अंडर
    0.68
     unittest
    0.68
     its
    0.68
     ]];
    0.67
     "))
    0.67
    POSITIVE LOGITS
    ricies
    0.82
    listed
    0.79
    घी
    0.78
    ಕಿ
    0.76
     publicados
    0.73
    amu
    0.72
    cheiden
    0.72
     Tätigkeit
    0.71
    ទៀ
    0.69
    roles
    0.68
    Activations Density 0.001%

    No Known Activations