© 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-16K
    7. 2979
    Prev
    Next
    INDEX
    Explanations

    medical advice and helplines

    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_16k_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
     हा
    0.67
     INTO
    0.63
     ти
    0.60
    Ре
    0.59
    ចុ
    0.57
     પ્ર
    0.57
     ຊ
    0.57
    滑动
    0.56
     otherwise
    0.56
    なければ
    0.55
    POSITIVE LOGITS
    osof
    0.78
    oves
    0.78
     capitán
    0.76
    military
    0.75
    freien
    0.75
    ariales
    0.74
    شفى
    0.73
    otification
    0.73
    ilitary
    0.73
     LMF
    0.72
    Activations Density 0.045%

    No Known Activations