© 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. 160514
    Prev
    Next
    INDEX
    Explanations

    click save logo

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

    specific feature

    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
    ز
    0.55
    би
    0.54
     бесплатно
    0.50
     ин
    0.49
     espont
    0.48
     coconut
    0.48
     alkaline
    0.47
    ковой
    0.46
     inmun
    0.45
     abond
    0.45
    POSITIVE LOGITS
     ศูนย์
    0.60
     Clos
    0.57
     หลังจาก
    0.55
     Resonance
    0.54
     Boot
    0.51
    पहरण
    0.51
    㑓
    0.51
    หลังจาก
    0.50
     לאחר
    0.50
     Counseling
    0.50
    Activations Density 0.001%

    No Known Activations