© 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. 43324
    Prev
    Next
    INDEX
    Explanations

    social and political issues

    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
     vena
    0.47
     bukti
    0.46
     wody
    0.46
     mesenchymal
    0.46
    hkse
    0.45
    ferm
    0.45
    deaths
    0.45
    <unused2064>
    0.45
    struktur
    0.45
     débat
    0.45
    POSITIVE LOGITS
     Krieg
    0.42
     Phoenix
    0.42
    Phoenix
    0.40
    ací
    0.39
     materialized
    0.39
     UserRepository
    0.39
     CDP
    0.38
     Huy
    0.37
    形势
    0.36
     Tu
    0.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.