© 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. 146073
    Prev
    Next
    INDEX
    Explanations

    gaming screens

    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
    듣
    0.71
    enol
    0.70
     imperio
    0.68
    вся
    0.67
    ट्टे
    0.67
    dois
    0.67
    💞
    0.65
    Callbacks
    0.65
     poils
    0.65
    篁
    0.64
    POSITIVE LOGITS
    UTONIUM
    0.94
    バン
    0.82
     Significantly
    0.80
    octagon
    0.80
    ోతి
    0.75
     Tanzania
    0.75
     Segment
    0.75
    ائج
    0.75
     SEG
    0.75
     trophy
    0.74
    Activations Density 0.000%

    No Known Activations