© 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. 90737
    Prev
    Next
    INDEX
    Explanations

    credit your trade-in

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

    foreign languages and scripts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    vi
    0.53
    urgia
    0.52
    /*
    0.50
    linson
    0.47
     अली
    0.46
    ziu
    0.46
    hemia
    0.46
    ovali
    0.45
    ussen
    0.45
    ieft
    0.45
    POSITIVE LOGITS
    ال
    0.45
     tribun
    0.45
    ป็น
    0.44
    らえる
    0.43
     بال
    0.42
     تلف
    0.42
     വ്യാപ
    0.42
    Љ
    0.42
    явления
    0.41
    AspectRatio
    0.41
    Activations Density 0.000%

    No Known Activations