© 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. 220916
    Prev
    Next
    INDEX
    Explanations

    sequence multipliers quantification quantifiers

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

    when describing conditions or requirements

    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
     അവ
    0.46
    ycznych
    0.43
    いくつかの
    0.43
     attribut
    0.43
     Pointer
    0.43
    ι
    0.43
     عض
    0.42
     −
    0.41
    个
    0.41
     个
    0.40
    POSITIVE LOGITS
    नेश्वर
    0.45
     ಬಿಜೆಪಿ
    0.45
    ኛውም
    0.44
    prosperity
    0.44
     பார்க்கும்
    0.43
     הע
    0.42
     एनर्जी
    0.42
    herlands
    0.41
     السيارة
    0.41
     EXPL
    0.40
    Activations Density 0.000%

    No Known Activations