© 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. 51685
    Prev
    Next
    INDEX
    Explanations

    `$+`

    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
     nieces
    0.43
    সুম
    0.37
     blamed
    0.36
    hende
    0.36
    跄
    0.35
     né
    0.34
     scaff
    0.34
    まん
    0.33
    endeu
    0.33
     책임
    0.33
    POSITIVE LOGITS
     $+$
    0.43
    $+
    0.42
     Öl
    0.41
    buk
    0.41
     rata
    0.39
    От
    0.39
     Santander
    0.39
     Lumia
    0.39
     Lutz
    0.38
     honestly
    0.38
    Activations Density 0.008%

    No Known Activations