© 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. 209799
    Prev
    Next
    INDEX
    Explanations

    Motorcycle Training, British Columbia

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

    why and reluctance

    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
    ককে
    0.50
    Riley
    0.50
    ਪਣ
    0.48
    我想
    0.48
    ඤ
    0.48
    임을
    0.47
    ╽
    0.47
    
    0.46
     lightness
    0.46
     dew
    0.46
    POSITIVE LOGITS
    gäng
    0.51
    leri
    0.50
    0.49
    ies
    0.49
    rä
    0.49
    ied
    0.45
    iter
    0.45
     პრო
    0.45
    access
    0.44
    termin
    0.44
    Activations Density 0.000%

    No Known Activations