© 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. 49029
    Prev
    Next
    INDEX
    Explanations

    `__name__`

    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
     मुश्किल
    0.48
    ⁈
    0.40
     सलूशन
    0.40
     समक्ष
    0.39
    မျှ
    0.39
     vermutlich
    0.38
     компен
    0.38
    !}
    0.38
    ılması
    0.37
     прогноз
    0.37
    POSITIVE LOGITS
    ა
    0.46
    울
    0.46
    šie
    0.43
    фек
    0.43
    つけ
    0.43
     ranged
    0.41
     overnight
    0.41
    ॉर्ट
    0.41
    ని
    0.40
     ಪ್ಯಾ
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.