© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45826
    Prev
    Next
    INDEX
    Explanations

    world descriptions and characteristics

    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
    ရား
    0.45
    گاهی
    0.44
    Union
    0.43
    膿
    0.43
    ed
    0.42
     dropping
    0.41
     پخش
    0.41
    hem
    0.41
    ing
    0.40
    ように
    0.40
    POSITIVE LOGITS
    
    0.46
     Nä
    0.44
     triển
    0.44
    Nä
    0.44
    Gün
    0.41
    }
    0.41
    ას
    0.41
     endeavours
    0.40
    isać
    0.39
    옥
    0.39
    Activations Density 0.003%

    No Known Activations