© 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. 64885
    Prev
    Next
    INDEX
    Explanations

    parsing emails, config, components

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

    code builders and parsers

    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
     الكهربائيه
    0.52
    मणि
    0.46
     વખતે
    0.46
     కీలక
    0.46
     فایل
    0.44
     वैक्सीन
    0.43
     مهمه
    0.43
    鹫
    0.43
     القناه
    0.42
     movingRect
    0.42
    POSITIVE LOGITS
     ANO
    0.59
     converters
    0.54
     Aix
    0.51
     Moroccan
    0.49
     Ely
    0.49
     counterparts
    0.47
     Kj
    0.47
     Gonz
    0.47
     Irm
    0.47
     EY
    0.47
    Activations Density 0.000%

    No Known Activations