© 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. 29847
    Prev
    Next
    INDEX
    Explanations

    structured data or descriptions

    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
     categories
    0.46
     devices
    0.45
     class
    0.44
     realms
    0.44
     measures
    0.42
     graces
    0.42
    з
    0.42
     /
    0.41
     classes
    0.41
    ver
    0.41
    POSITIVE LOGITS
    痙
    0.49
    疠
    0.48
    ლება
    0.48
    რულ
    0.46
    rollerskates
    0.46
    ungkinkan
    0.43
    kiyor
    0.43
    Chào
    0.43
     История
    0.43
     pushedAt
    0.43
    Activations Density 0.000%

    No Known Activations