© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 183302
    Prev
    Next
    INDEX
    Explanations

    selection of description and subsequent outcome

    np_acts-logits-general · gemini-2.5-flash-lite

    fee paid, former president

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    mens
    0.50
    manuel
    0.47
     tangents
    0.47
    idades
    0.46
    ña
    0.46
    brar
    0.46
    ́
    0.46
    ître
    0.45
    fonos
    0.45
    Tangent
    0.45
    POSITIVE LOGITS
    奥运
    0.48
    结局
    0.47
    烣
    0.47
     Candidate
    0.47
     省
    0.46
    енти
    0.46
    宫
    0.44
    他在
    0.43
     食
    0.43
     Sees
    0.43
    Activations Density 0.000%

    No Known Activations