© 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. 137981
    Prev
    Next
    INDEX
    Explanations

    numbers, codes, and identifiers

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

    types and return values

    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
    ан
    0.26
    ↵
    0.25
    ஆனால்
    0.24
    આ
    0.24
     (
    0.24
    redients
    0.23
    АН
    0.23
    🥇
    0.23
    阿里云
    0.23
    ஏ
    0.22
    POSITIVE LOGITS
     de
    0.25
     del
    0.23
     trimester
    0.23
     thermocouple
    0.21
     inflex
    0.21
     gráf
    0.21
     disapp
    0.21
     butyl
    0.21
     methylene
    0.20
     approvals
    0.20
    Activations Density 0.072%

    No Known Activations