© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8820
    Prev
    Next
    INDEX
    Explanations

    phonetical speech / game mechanics / technical terms

    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
     The
    0.26
     G
    0.25
     H
    0.25
     D
    0.25
     M
    0.24
     V
    0.23
     T
    0.23
     P
    0.23
     In
    0.23
     Portland
    0.23
    POSITIVE LOGITS
     substring
    0.24
     operands
    0.24
     diarrh
    0.24
     indiquer
    0.22
    Missense
    0.22
     viande
    0.22
     symbolTable
    0.22
     malonyl
    0.22
     grammaticality
    0.22
     dhatu
    0.22
    Activations Density 0.238%

    No Known Activations