© 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. 75721
    Prev
    Next
    INDEX
    Explanations

    multilingual word selections

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

    API providers or web technologies

    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
    ২৭
    0.52
    ა
    0.50
    銷
    0.50
    纖
    0.49
    嚴
    0.48
    濾
    0.48
    ਠ
    0.47
    TD
    0.47
    餓
    0.47
    ਤੀ
    0.46
    POSITIVE LOGITS
    ומר
    0.48
     auswählen
    0.46
    erdings
    0.45
    )،
    0.45
     önceki
    0.44
     அரசின்
    0.43
    öy
    0.43
    ümüzde
    0.43
     choisir
    0.42
    йл
    0.42
    Activations Density 0.000%

    No Known Activations