© 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. 208338
    Prev
    Next
    INDEX
    Explanations

    choice, freedom, York, prior

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

    | risk assessment

    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
    ify
    0.52
     i
    0.50
     Auditorium
    0.50
     bathrooms
    0.48
     auditorium
    0.47
     I
    0.45
     Lake
    0.45
     Earth
    0.45
     England
    0.45
     overburden
    0.45
    POSITIVE LOGITS
     ساعة
    0.54
     لوبه
    0.53
     وړاندوینې
    0.50
     მნიშვნელ
    0.49
    产
    0.48
     explicação
    0.47
     வெங்க
    0.47
    娅
    0.47
     அமைப்பு
    0.47
     இரண்டு
    0.47
    Activations Density 0.001%

    No Known Activations