© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 74772
    Prev
    Next
    INDEX
    Explanations

    available through brands and names

    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
    Negative Logits
    ⵔ
    0.49
    Ꮺ
    0.46
     persuaded
    0.46
     néanmoins
    0.45
     tuttavia
    0.45
    িলের
    0.44
     tensão
    0.43
     towed
    0.43
    㸳
    0.43
     নির্মান
    0.41
    POSITIVE LOGITS
    d
    0.57
    da
    0.54
    u
    0.50
     W
    0.47
    data
    0.47
    g
    0.47
            
    0.46
    dye
    0.46
    den
    0.45
    w
    0.45
    Activations Density 0.006%

    No Known Activations