© 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. 130499
    Prev
    Next
    INDEX
    Explanations

    specific followed words

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

    identify or figure out

    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
     a
    0.49
    sb
    0.47
    0.46
     Phrases
    0.45
     ö
    0.41
    take
    0.41
     Phrase
    0.41
     Buff
    0.41
    takes
    0.41
     take
    0.40
    POSITIVE LOGITS
    testX
    0.49
    চা
    0.48
    مانی
    0.48
     Высо
    0.47
    ExposureTime
    0.47
    ಷ್ಠ
    0.47
    मिटेड
    0.46
    мес
    0.46
    ⚤
    0.46
    вости
    0.46
    Activations Density 0.002%

    No Known Activations