© 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. 146828
    Prev
    Next
    INDEX
    Explanations

    can't quite name

    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
    orthy
    0.64
    ‛
    0.64
    Day
    0.63
     peppers
    0.62
    ຝ
    0.62
     calories
    0.62
     envisage
    0.62
     Personen
    0.61
    処分
    0.61
    袱
    0.61
    POSITIVE LOGITS
    enc
    0.79
    いう
    0.78
    tten
    0.76
     Ayala
    0.75
     resultCode
    0.75
     இல்ல
    0.75
    䅞
    0.74
    subTest
    0.73
    ма
    0.73
    idente
    0.72
    Activations Density 0.001%

    No Known Activations