© 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-65K
    7. 54840
    Prev
    Next
    INDEX
    Explanations

    options, variety, focus

    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_65k_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
    ר
    0.47
     Joan
    0.47
     shawl
    0.46
     Cosmetic
    0.45
     Pompe
    0.45
     இருக்கலாம்
    0.44
     Benzema
    0.44
     Michelle
    0.44
     alloying
    0.44
     Coachella
    0.44
    POSITIVE LOGITS
    dte
    0.47
    balls
    0.45
    bells
    0.45
     nuevos
    0.43
    lems
    0.43
    뎐
    0.43
    carts
    0.42
    crackers
    0.42
    sessions
    0.42
     ácidos
    0.42
    Activations Density 0.001%

    No Known Activations