© 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. 130471
    Prev
    Next
    INDEX
    Explanations

    phrases and specific nouns

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

    transportation, alternatives, recommendations

    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
    変更
    0.49
     recycle
    0.44
     changement
    0.42
     render
    0.42
     окт
    0.42
     convolution
    0.42
    夯
    0.41
     glyph
    0.41
     trench
    0.41
    更改
    0.41
    POSITIVE LOGITS
    
    0.50
    aranteed
    0.50
    ั
    0.49
    loir
    0.47
     veinte
    0.46
    =-\
    0.46
     दिखाते
    0.45
    סי
    0.45
    ksjon
    0.45
    ท่าน
    0.45
    Activations Density 0.000%

    No Known Activations