© 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. 36455
    Prev
    Next
    INDEX
    Explanations

    recommendations for events

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

    ways to describe options

    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
    бом
    0.47
    慘
    0.46
     Barber
    0.46
    ев
    0.45
     चिंग
    0.44
    كه
    0.44
     NSD
    0.44
    방송
    0.44
     Aquatic
    0.44
     moo
    0.43
    POSITIVE LOGITS
     parameter
    0.52
    ltre
    0.49
     মুখ
    0.49
     부분을
    0.49
     उतारा
    0.49
     এ
    0.47
     çıkarm
    0.46
     بنائے
    0.46
     শীর্ষ
    0.46
     turi
    0.45
    Activations Density 0.000%

    No Known Activations