© 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. 22-GEMMASCOPE-2-RES-262K
    7. 5296
    Prev
    Next
    INDEX
    Explanations

    did the joke questions

    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_22_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
     (
    0.69
     pre
    0.67
    ness
    0.67
    ris
    0.64
    ens
    0.62
     trials
    0.62
     ethn
    0.62
     interceptions
    0.62
     me
    0.61
     sap
    0.61
    POSITIVE LOGITS
    鉐
    0.93
     guerre
    0.92
     さらに
    0.89
    Пла
    0.88
    elemento
    0.83
    Usuario
    0.82
    iciente
    0.82
    usuario
    0.82
     Jeśli
    0.80
     Мето
    0.79
    Activations Density 0.004%

    No Known Activations