© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 17085
    Prev
    Next
    INDEX
    Explanations

    bathroom renovation

    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_16_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
     devour
    0.84
     למ
    0.78
    ?
    0.78
    ﺍ
    0.76
    ﻕ
    0.73
     vigente
    0.73
     went
    0.71
     drew
    0.70
    ﻑ
    0.70
    Vic
    0.69
    POSITIVE LOGITS
    ص
    0.87
     or
    0.81
    ang
    0.79
    il
    0.78
    дар
    0.76
    ня
    0.75
    ס
    0.73
    alities
    0.73
    urine
    0.72
    ir
    0.71
    Activations Density 0.002%

    No Known Activations