© 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-262K
    7. 110035
    Prev
    Next
    INDEX
    Explanations

    languages and structured text

    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_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
     app
    0.46
     ogr
    0.44
    隴
    0.44
    绫
    0.44
     ofx
    0.44
     ofApp
    0.43
     senses
    0.43
    魍
    0.43
     أيام
    0.42
     মর্
    0.42
    POSITIVE LOGITS
     minced
    0.44
     हमने
    0.42
     ധാ
    0.42
     Кири
    0.42
     मिन
    0.42
     whipped
    0.42
    imos
    0.41
     самостоя
    0.41
    بلی
    0.41
     открытия
    0.41
    Activations Density 0.002%

    No Known Activations