© 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. 227620
    Prev
    Next
    INDEX
    Explanations

    South Africa directly to controlling

    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
    🩺
    0.57
    дневно
    0.57
    𝙙
    0.57
     кілько
    0.55
    ồm
    0.53
    Дан
    0.53
     부정
    0.53
    dienst
    0.53
    𝗱
    0.52
    ứng
    0.52
    POSITIVE LOGITS
     you
    0.55
     couple
    0.51
     refresher
    0.48
     window
    0.48
     símbolo
    0.47
    -
    0.47
     engine
    0.46
     brick
    0.46
     controller
    0.45
     city
    0.45
    Activations Density 0.000%

    No Known Activations