© 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. 187128
    Prev
    Next
    INDEX
    Explanations

    website and official terms

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

    brush dog regularly

    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
     φι
    0.46
    ically
    0.45
    ícia
    0.45
     信息
    0.45
    comes
    0.45
    信息
    0.45
    大规模
    0.45
    郫
    0.45
    务
    0.45
    ctors
    0.44
    POSITIVE LOGITS
     Bereichen
    0.46
     मिलियन
    0.45
    াদনের
    0.44
    蒾
    0.44
    মের
    0.44
     krem
    0.43
    ohm
    0.42
    CRL
    0.42
     Schad
    0.42
    million
    0.41
    Activations Density 0.000%

    No Known Activations