© 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. 134043
    Prev
    Next
    INDEX
    Explanations

    matches, paragraph, new, theatre, choice

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

    mention specific details

    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
    نڈ
    0.55
    اک
    0.50
    年に
    0.48
    ത
    0.48
    二年
    0.47
    ری
    0.46
    кові
    0.46
    вена
    0.45
    ولی
    0.44
    دو
    0.44
    POSITIVE LOGITS
     :{
    0.49
    :{
    0.48
     spurs
    0.48
     הי
    0.47
    ḧ
    0.47
    }.
    0.46
    isActive
    0.46
     ملعب
    0.45
    }}{
    0.44
     urls
    0.44
    Activations Density 0.000%

    No Known Activations