© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22484
    Prev
    Next
    INDEX
    Explanations

    describing specific concepts or actions

    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
    yuan
    0.46
    cosity
    0.46
    Reception
    0.42
    ****/
    0.42
     precipitation
    0.40
     synonyms
    0.40
     exceeding
    0.39
     excavation
    0.39
     artificielle
    0.39
     diffusion
    0.39
    POSITIVE LOGITS
     Batman
    0.44
    書
    0.43
     particolarmente
    0.42
    ء
    0.42
    CON
    0.41
     Siamo
    0.41
    بح
    0.40
     Cinderella
    0.39
     ملے
    0.39
     modellen
    0.39
    Activations Density 0.000%

    No Known Activations