© 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-262K
    7. 130582
    Prev
    Next
    INDEX
    Explanations

    technical or creative text completion

    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_262k_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
    K
    0.42
    GINIA
    0.41
     authenticated
    0.40
    l
    0.40
    authenticated
    0.40
     entr
    0.38
    k
    0.38
    arry
    0.38
    DA
    0.37
     loved
    0.37
    POSITIVE LOGITS
    盽
    0.44
    ଳ
    0.41
     ("/
    0.41
     '.';
    0.41
     ওঠা
    0.41
    昦
    0.41
     declinations
    0.40
    (/(
    0.40
     subgroup
    0.40
     Grup
    0.39
    Activations Density 0.000%

    No Known Activations