© 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. 127932
    Prev
    Next
    INDEX
    Explanations

    technical, informal, and specific nouns

    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
    郧
    0.50
    utivo
    0.49
    восто
    0.47
    ূতন
    0.46
    裕
    0.45
     mại
    0.45
     próxim
    0.44
    崤
    0.44
     Maurizio
    0.43
    izieren
    0.43
    POSITIVE LOGITS
    את
    0.50
    가
    0.49
    ცა
    0.45
     that
    0.45
    רה
    0.45
    を
    0.43
    را
    0.42
    ми
    0.42
     bulbs
    0.42
     esophagus
    0.42
    Activations Density 0.000%

    No Known Activations