© 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. 62752
    Prev
    Next
    INDEX
    Explanations

    NgModule and Module declarations

    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
    fjord
    0.43
     समाजवादी
    0.40
     hypothalam
    0.39
    ியே
    0.39
     मानना
    0.39
    yuk
    0.39
    diy
    0.39
    蛆
    0.38
     Owl
    0.38
     cnv
    0.38
    POSITIVE LOGITS
    ،
    0.49
     보통
    0.45
    Return
    0.40
     ,
    0.39
     바
    0.39
     bater
    0.39
    แบ
    0.39
    ின
    0.38
    ARIOS
    0.38
    Inserting
    0.37
    Activations Density 0.001%

    No Known Activations