© 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. 169175
    Prev
    Next
    INDEX
    Explanations

    foreign languages and names

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

    foreign characters or symbols

    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
     nums
    0.47
     CuSO
    0.46
     stupidity
    0.45
    ማ
    0.44
     futbolista
    0.44
     cyn
    0.44
     lao
    0.43
     hostilities
    0.43
     guerras
    0.43
    आज
    0.43
    POSITIVE LOGITS
    িকারী
    0.49
     Kaufmann
    0.47
    uliert
    0.47
     막
    0.47
    หาคม
    0.46
    㑼
    0.46
    的问题
    0.45
    ienten
    0.45
    }}/
    0.45
    minton
    0.44
    Activations Density 0.001%

    No Known Activations