© 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. 70705
    Prev
    Next
    INDEX
    Explanations

    change, customer, upgrade

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

    outcomes and conditions

    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
     этот
    0.45
     Этот
    0.45
    тьми
    0.44
    ༸
    0.44
    payroll
    0.42
    
    0.42
    ட்டில்
    0.41
    ियस
    0.40
    unut
    0.40
    몇
    0.39
    POSITIVE LOGITS
    dN
    0.52
     sû
    0.50
    日起
    0.48
    dV
    0.47
     avanz
    0.46
     offenbar
    0.46
     ducha
    0.45
     Neuros
    0.45
     bagno
    0.45
     blueprints
    0.44
    Activations Density 0.001%

    No Known Activations