© 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. 79193
    Prev
    Next
    INDEX
    Explanations

    Basket style, oven style

    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
     있
    0.51
     괴
    0.46
     lobes
    0.43
     locales
    0.43
     airfield
    0.43
     والا
    0.41
     maç
    0.41
     крова
    0.40
     grapefruit
    0.40
    Bert
    0.39
    POSITIVE LOGITS
     Stop
    0.47
     Referred
    0.43
    स्टेंस
    0.40
    頓
    0.40
    धरी
    0.39
    れている
    0.39
     Happened
    0.39
    製作
    0.39
     Pull
    0.39
     CONTRIBUT
    0.39
    Activations Density 0.001%

    No Known Activations