© 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. 102180
    Prev
    Next
    INDEX
    Explanations

    links support benefit

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

    potential danger or damages

    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
    جمع
    0.49
    ницей
    0.48
    員工
    0.47
     Frau
    0.47
    ந்த
    0.46
    न्छ
    0.46
    нку
    0.46
    ٤
    0.46
    大學
    0.45
    鈦
    0.45
    POSITIVE LOGITS
     arsenal
    0.54
     Authorized
    0.52
     appalling
    0.51
    ada
    0.50
     ugly
    0.50
     abys
    0.50
     ADA
    0.50
     authorized
    0.50
     odyssey
    0.50
     patriotism
    0.50
    Activations Density 0.000%

    No Known Activations