© 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. 2670
    Prev
    Next
    INDEX
    Explanations

    special characters and newlines

    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
    器的
    0.92
     concentrated
    0.72
    器
    0.71
     PH
    0.65
     Te
    0.64
     coordinate
    0.64
     ll
    0.63
    кое
    0.61
     ร
    0.61
    ர
    0.60
    POSITIVE LOGITS
    nYou
    0.82
    f
    0.80
    ffield
    0.78
    nThe
    0.74
    fdata
    0.74
    u
    0.71
    <unused1797>
    0.70
    zA
    0.69
    d
    0.69
    identité
    0.69
    Activations Density 0.140%

    No Known Activations