© 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. 55878
    Prev
    Next
    INDEX
    Explanations

    identities revealed or deciphered

    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
    Occasionally
    0.43
     허
    0.42
    허
    0.41
     Occasionally
    0.40
    شي
    0.38
    Spend
    0.37
    Hes
    0.36
    CAN
    0.36
     relo
    0.36
    쎈
    0.36
    POSITIVE LOGITS
    oved
    0.39
    aisi
    0.39
    ensin
    0.39
    珼
    0.38
    ArchiveAction
    0.38
     combinatorial
    0.37
    ází
    0.37
    (/\
    0.36
    antics
    0.35
     combin
    0.35
    Activations Density 0.006%

    No Known Activations