© 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. 242284
    Prev
    Next
    INDEX
    Explanations

    verified Auto Mechanic

    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
    ом
    0.55
     qubits
    0.50
    |.|.|
    0.45
    КИ
    0.45
    әм
    0.45
    слова
    0.45
    ಭ
    0.45
     키
    0.44
     पुष्
    0.44
    лью
    0.44
    POSITIVE LOGITS
    orgeous
    0.49
     Mou
    0.47
     Revenue
    0.45
    ième
    0.45
     Stras
    0.45
     Democratic
    0.44
     Einkauf
    0.44
     Sanctuary
    0.43
     abandonar
    0.43
     revenue
    0.43
    Activations Density 0.001%

    No Known Activations