© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203550
    Prev
    Next
    INDEX
    Explanations

    key of C

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    괵
    0.46
     promul
    0.45
    ENG
    0.45
     mesures
    0.45
     crushes
    0.44
     cuidar
    0.44
    முறை
    0.44
    RI
    0.43
     setText
    0.43
     repos
    0.42
    POSITIVE LOGITS
    0.49
    hole
    0.45
    帮
    0.44
    色的
    0.43
    с
    0.43
    ս
    0.43
    -
    0.42
    uffer
    0.41
    存储
    0.41
    Ticket
    0.40
    Activations Density 0.001%

    No Known Activations