© 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. 199991
    Prev
    Next
    INDEX
    Explanations

    will only calculated monitor professionals under known all number Control

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

    text generation following certain prompts

    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
    *'
    0.55
    不说
    0.52
    داری
    0.52
    عرف
    0.50
    روح
    0.50
    籾
    0.49
    还没
    0.48
    *',
    0.48
    Secondo
    0.48
    磴
    0.46
    POSITIVE LOGITS
    ira
    0.50
     highlighted
    0.48
    mond
    0.47
     мотива
    0.47
    ína
    0.47
    okol
    0.47
    fal
    0.46
     こと
    0.46
     zari
    0.46
     emble
    0.45
    Activations Density 0.000%

    No Known Activations