© 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. 5315
    Prev
    Next
    INDEX
    Explanations

    Python code snippets

    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
    KI
    0.51
    3
    0.48
    好
    0.47
    aro
    0.45
     উপযোগী
    0.45
    2
    0.42
    多
    0.42
    IB
    0.41
    는
    0.41
    PI
    0.41
    POSITIVE LOGITS
    smittel
    0.48
    }}$,
    0.45
    ującego
    0.44
     jede
    0.44
    ్యం
    0.43
    wärt
    0.42
     verwendeten
    0.42
     경우는
    0.41
     الاق
    0.41
     fährt
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.