© 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. 22323
    Prev
    Next
    INDEX
    Explanations

    words starting with Pas

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

    common names, states, controllers

    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
     сертифика
    0.46
    avacan
    0.44
     PERCENT
    0.44
     Шрифт
    0.44
     Salary
    0.43
     вдох
    0.43
     COMPENSATION
    0.42
    违
    0.42
     Died
    0.41
    灵魂
    0.41
    POSITIVE LOGITS
    難
    0.42
    ranked
    0.40
     خصوص
    0.38
    情报
    0.38
    stery
    0.38
    ,
    0.38
    jammer
    0.38
    ემის
    0.37
    ]',
    0.36
     ಹಾಗೂ
    0.36
    Activations Density 0.001%

    No Known Activations