© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46753
    Prev
    Next
    INDEX
    Explanations

    advanced medical

    np_acts-logits-general · gemini-2.5-flash-lite

    help with writing offers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     подоб
    0.43
    ✚
    0.42
     스
    0.42
    댐
    0.42
     엄청
    0.41
     &
    0.41
    کس
    0.40
     புதிய
    0.40
     Nowhere
    0.40
    Be
    0.40
    POSITIVE LOGITS
     secretary
    0.46
    酌
    0.45
    mang
    0.44
     routing
    0.44
    रुख
    0.43
     पेड़
    0.43
     रोकथाम
    0.43
    Secretary
    0.42
     অবগত
    0.42
     inhibited
    0.42
    Activations Density 0.000%

    No Known Activations