© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57643
    Prev
    Next
    INDEX
    Explanations

    social, democratic, family, support

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

    policy outcomes

    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
    Not in Any Lists

    No Comments

    Negative Logits
     phénomènes
    0.54
     bialgebras
    0.54
     vascul
    0.51
    kran
    0.51
     ℝ
    0.50
     Aś
    0.49
     atthakath
    0.49
     itinéraires
    0.48
     obstru
    0.48
     विमान
    0.48
    POSITIVE LOGITS
     sustainable
    0.49
     middle
    0.44
     social
    0.44
     democratic
    0.42
    ised
    0.41
     sociable
    0.40
    中
    0.40
    法
    0.39
     vibrancy
    0.39
    爱
    0.39
    Activations Density 0.000%

    No Known Activations