© 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. 220840
    Prev
    Next
    INDEX
    Explanations

    president, fund, examine, within, function

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

    strategy and planning instructions

    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
    crystalline
    0.50
    ७
    0.50
     purest
    0.46
    ᱓
    0.45
     ಉತ್ಪ
    0.45
    ᱕
    0.45
    Protein
    0.45
     लार्
    0.44
     உற்ப
    0.44
    渟
    0.43
    POSITIVE LOGITS
    ydi
    0.44
     accessoires
    0.43
    แจ้ง
    0.43
     shortcuts
    0.42
     nicknames
    0.42
     kombin
    0.42
     dodat
    0.42
     zelf
    0.42
     spectrogram
    0.41
     phrases
    0.41
    Activations Density 0.002%

    No Known Activations