© 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. 63735
    Prev
    Next
    INDEX
    Explanations

    personal and collective actions

    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
    がいい
    0.46
    吩
    0.42
     teak
    0.42
    if
    0.42
    ちょっと
    0.41
     blistering
    0.41
    કો
    0.41
    ns
    0.41
    nosť
    0.41
    体操
    0.41
    POSITIVE LOGITS
     individuelle
    0.52
     Londres
    0.47
    ▹
    0.46
     tät
    0.46
     entice
    0.46
     जिज्ञा
    0.45
     çant
    0.44
     segundo
    0.44
     individu
    0.44
     व्यक्तिगत
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.