© 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. 209759
    Prev
    Next
    INDEX
    Explanations

    lists of businesses

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

    user or model questions

    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
     çünkü
    0.57
    ᱾
    0.54
     svojoj
    0.53
    ınt
    0.50
    ELSE
    0.50
     সংগ্রহের
    0.48
    İstanbul
    0.48
     savo
    0.47
     prosegu
    0.46
     informacion
    0.46
    POSITIVE LOGITS
    minton
    0.50
    ป์
    0.50
    ے
    0.50
    рка
    0.49
    لى
    0.46
    drawable
    0.45
     fisherman
    0.45
    س
    0.45
     settings
    0.45
     setter
    0.44
    Activations Density 0.001%

    No Known Activations