© 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. 166050
    Prev
    Next
    INDEX
    Explanations

    crew members, overnight fabricate, medal finish

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

    imaginary, virtual, splitting, medical

    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
    ↵
    0.54
     opinion
    0.46
     fix
    0.45
    ↵↵
    0.44
     exposure
    0.44
     retaining
    0.44
     is
    0.43
     staple
    0.43
     retain
    0.43
    ।
    0.42
    POSITIVE LOGITS
     時計
    0.52
     fréquemment
    0.51
    atthaya
    0.50
    ologio
    0.49
    ;|&
    0.48
    🔡
    0.48
     અથ
    0.47
    ACI
    0.47
    otomy
    0.46
     nahezu
    0.46
    Activations Density 0.001%

    No Known Activations