© 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. 8335
    Prev
    Next
    INDEX
    Explanations

    punctuation and connectors

    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
     مذ
    0.38
    Acetoxy
    0.36
    褂
    0.35
    addena
    0.35
     wikipagina
    0.35
    lą
    0.35
    xcsche
    0.34
    GTUIKit
    0.34
     Фургала
    0.34
     टेंपरेचर
    0.34
    POSITIVE LOGITS
     and
    0.54
     containing
    0.38
     आणि
    0.38
     और
    0.38
     sich
    0.38
    与
    0.38
     whose
    0.37
     die
    0.37
     eight
    0.37
     மற்றும்
    0.36
    Activations Density 0.349%

    No Known Activations