© 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. 45676
    Prev
    Next
    INDEX
    Explanations

    medical benefits

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

    styles and services

    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
     Fairchild
    0.55
     setIs
    0.52
     ডেভেল
    0.49
     laughable
    0.49
    ної
    0.49
    кої
    0.48
    🫣
    0.48
     మూవీ
    0.48
    魧
    0.47
     שלא
    0.47
    POSITIVE LOGITS
    ergy
    0.51
    ftan
    0.47
     intensification
    0.46
     satiety
    0.46
    umab
    0.46
    acting
    0.44
    absorbed
    0.44
    arc
    0.44
    jz
    0.43
     absorbers
    0.43
    Activations Density 0.000%

    No Known Activations