© 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. 178345
    Prev
    Next
    INDEX
    Explanations

    articles mentioning availability and help

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

    limitations and warnings

    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
     concedes
    0.47
     Geheim
    0.47
    c
    0.46
    g
    0.46
     informe
    0.45
     dire
    0.45
     enorm
    0.45
    RV
    0.45
     RV
    0.44
     defiant
    0.44
    POSITIVE LOGITS
    蝦
    0.46
    لاص
    0.45
     الإنسان
    0.44
    ંમે
    0.44
    oxylated
    0.44
    燄
    0.44
     সাঁ
    0.42
    yecto
    0.41
    otsu
    0.41
    壓
    0.40
    Activations Density 0.002%

    No Known Activations