© 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. 152806
    Prev
    Next
    INDEX
    Explanations

    powering electronics and building

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

    foreign language elements

    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
    stown
    0.48
     Serious
    0.44
    只需
    0.43
     Amateur
    0.42
    auce
    0.41
     +
    0.41
     Policy
    0.41
    饵
    0.40
     bury
    0.40
    だけでも
    0.39
    POSITIVE LOGITS
     copiar
    0.47
     dado
    0.47
     اپنی
    0.46
     رکھیں
    0.46
     ہمارا
    0.46
    nsan
    0.45
     galerinha
    0.44
     navegador
    0.44
     possibile
    0.43
     રાખ
    0.43
    Activations Density 0.001%

    No Known Activations