© 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. 7527
    Prev
    Next
    INDEX
    Explanations

    category and its descriptor

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

    crisis lifeline

    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
    󰀄
    0.31
    ஜ்மஹால்
    0.29
     spacetime
    0.29
     vaginale
    0.29
    തിനാൽ
    0.29
    ⵕ
    0.29
     mâles
    0.29
     erreur
    0.28
    摖
    0.28
     eyelashes
    0.28
    POSITIVE LOGITS
    encour
    0.26
     Society
    0.26
    ‹
    0.25
     &
    0.24
     I
    0.24
    S
    0.24
    са
    0.24
     A
    0.23
    FACE
    0.23
     Consortium
    0.23
    Activations Density 0.597%

    No Known Activations