© 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. 3900
    Prev
    Next
    INDEX
    Explanations

    expert initialization functions

    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
    DIRECTION
    0.41
    Direction
    0.40
     Direction
    0.40
    colorChoice
    0.39
     DIRECTION
    0.39
    榄
    0.38
     гало
    0.38
    ClInclude
    0.37
    TRANSFER
    0.37
    evenly
    0.37
    POSITIVE LOGITS
     Glyph
    0.45
    cand
    0.38
     stood
    0.37
    Gly
    0.36
     glyph
    0.36
    Pool
    0.35
     Auf
    0.34
    cation
    0.34
     /=
    0.34
    Ба
    0.34
    Activations Density 0.015%

    No Known Activations