© 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. 211615
    Prev
    Next
    INDEX
    Explanations

    cylindrical label

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

    what follows

    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
    ات
    0.54
    зывают
    0.50
     Toolkit
    0.49
     दशकों
    0.46
     तुलना
    0.46
    टाइम
    0.45
     площад
    0.45
     огра
    0.45
    단계
    0.45
    ন
    0.45
    POSITIVE LOGITS
    boa
    0.54
     l
    0.47
     hors
    0.47
    IFS
    0.46
    cha
    0.46
    iet
    0.45
    ministrazione
    0.45
     já
    0.44
    ð
    0.44
    inea
    0.44
    Activations Density 0.000%

    No Known Activations