© 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. 69645
    Prev
    Next
    INDEX
    Explanations

    wife, ankle

    np_acts-logits-general · gemini-2.5-flash-lite

    variable assignments and function arguments

    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
     noqa
    0.43
    ূপ
    0.39
     条件
    0.38
    fulfilled
    0.36
     )
    0.36
    )|
    0.36
    ),]
    0.35
    }]
    0.35
     Ple
    0.35
     広
    0.35
    POSITIVE LOGITS
    मॉडल
    0.43
    モー
    0.41
    করিয়
    0.41
    ുവരി
    0.40
     perd
    0.39
    ळ्या
    0.39
    Bueno
    0.38
     annihil
    0.38
     ગા
    0.38
     convertir
    0.38
    Activations Density 0.019%

    No Known Activations