© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 147975
    Prev
    Next
    INDEX
    Explanations

    greater than, from sklearn

    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
     干
    0.75
    addContainer
    0.74
     Honest
    0.66
     እ
    0.65
    cée
    0.63
    カー
    0.63
     cement
    0.63
     ordre
    0.63
     caucus
    0.63
     KE
    0.62
    POSITIVE LOGITS
    ඤ
    0.69
    ್ಯ
    0.67
     हू
    0.66
     psicología
    0.64
    ズル
    0.64
     உருவாக
    0.64
     psychologist
    0.64
    iam
    0.63
     تح
    0.63
     psychologists
    0.63
    Activations Density 0.002%

    No Known Activations