© 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-65K
    7. 3330
    Prev
    Next
    INDEX
    Explanations

    helpline numbers or seeking help

    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_65k_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
    isteria
    0.80
    imi
    0.72
    徘
    0.72
     refrain
    0.72
    شاه
    0.71
    бто
    0.70
     मार्
    0.70
    ழை
    0.68
    ubahan
    0.68
     K
    0.66
    POSITIVE LOGITS
     mathematically
    0.70
     treating
    0.67
    deleteOne
    0.67
     tratar
    0.67
     loosely
    0.65
    koz
    0.64
     끌
    0.63
    郆
    0.61
     Recycle
    0.60
     textbooks
    0.60
    Activations Density 0.007%

    No Known Activations