© 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. 40-GEMMASCOPE-2-RES-65K
    7. 48183
    Prev
    Next
    INDEX
    Explanations

    Murray names and burn concepts

    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_40_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
     degener
    0.39
     burning
    0.39
    burning
    0.39
    Quer
    0.39
    presented
    0.39
    Cel
    0.38
    SdkVersion
    0.38
    3
    0.38
    Gameplay
    0.37
    槃
    0.37
    POSITIVE LOGITS
    気に
    0.39
     plan
    0.38
     zoo
    0.38
     custodian
    0.38
     Battle
    0.37
    山市
    0.37
     Jenny
    0.37
     Ob
    0.37
     jar
    0.37
    িয়ার
    0.37
    Activations Density 0.006%

    No Known Activations