© 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. 123338
    Prev
    Next
    INDEX
    Explanations

    phrases following common words

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

    than the acknowledgement of Calculate

    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
    Rights
    0.52
     హై
    0.51
    ⌋
    0.50
    ACO
    0.47
     Patrim
    0.46
    FormProvider
    0.46
    Schedule
    0.46
    Coal
    0.46
    Resident
    0.45
    Compat
    0.45
    POSITIVE LOGITS
    氣
    0.55
     ব্যক্তিগত
    0.54
     lucht
    0.50
     répondre
    0.48
     identificar
    0.46
    печат
    0.46
    そこで
    0.45
     acet
    0.45
     предложи
    0.45
     কর্তব্য
    0.45
    Activations Density 0.000%

    No Known Activations