© 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. 201887
    Prev
    Next
    INDEX
    Explanations

    authenticity or revenue

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

    understanding requirements and actions

    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
     servizio
    0.51
     protezione
    0.50
     differentiable
    0.47
    ಂಕ
    0.47
    滬
    0.46
     hạt
    0.45
     connexion
    0.45
     diagnóstico
    0.45
    や
    0.45
    桿
    0.45
    POSITIVE LOGITS
    ilen
    0.54
    undance
    0.48
     Narendra
    0.48
    ilet
    0.48
     توسط
    0.47
    uncio
    0.47
     exclu
    0.47
    esti
    0.47
    veren
    0.46
    urney
    0.46
    Activations Density 0.001%

    No Known Activations