© 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. 221396
    Prev
    Next
    INDEX
    Explanations

    want to

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

    foreign characters or multiple languages

    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
     pour
    0.52
    蜚
    0.47
    <0x91>
    0.47
    蛊
    0.46
    ר
    0.46
    일에
    0.44
    足够的
    0.43
    ]}'
    0.43
    ទ
    0.42
    成为了
    0.42
    POSITIVE LOGITS
    ^{*}=\
    0.48
     страхо
    0.46
     legislator
    0.43
    settes
    0.43
    देशक
    0.42
     учитель
    0.42
     Bi
    0.42
     EDF
    0.42
    InBuffer
    0.42
    kker
    0.41
    Activations Density 0.001%

    No Known Activations