© 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. 146942
    Prev
    Next
    INDEX
    Explanations

    M words following specific prompts

    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
    誒
    0.80
    狠
    0.80
     bioactive
    0.79
     dépasse
    0.78
    סט
    0.77
    ecirc
    0.76
    цах
    0.76
    酸化
    0.76
    ዓ
    0.75
     qualitatively
    0.75
    POSITIVE LOGITS
     m
    0.70
    m
    0.70
    м
    0.67
     mist
    0.67
     miss
    0.66
    miss
    0.66
     M
    0.66
    M
    0.66
     Mist
    0.65
     mis
    0.65
    Activations Density 0.001%

    No Known Activations