© 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. 228665
    Prev
    Next
    INDEX
    Explanations

    specific phrases and actions

    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
    inės
    0.51
    綎
    0.49
    ग्गा
    0.48
     следующих
    0.48
    िंक
    0.48
    рома
    0.48
    сных
    0.46
    сным
    0.46
    сер
    0.46
    بے
    0.46
    POSITIVE LOGITS
    🔫
    0.49
     finito
    0.46
    ahrenheit
    0.45
     Emission
    0.45
     ನಡೆದ
    0.44
     Afghanistan
    0.44
    GISLATIVE
    0.43
     suspensión
    0.43
     Ejecutivo
    0.43
     Finale
    0.42
    Activations Density 0.000%

    No Known Activations