© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 120368
    Prev
    Next
    INDEX
    Explanations

    constructor code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Какие
    0.40
    ющиеся
    0.40
     Hoboken
    0.38
     клиентов
    0.37
    <0x8C>
    0.37
     клиен
    0.37
    getRequest
    0.37
     بكم
    0.37
    ದಗ
    0.36
    鏄
    0.36
    POSITIVE LOGITS
     haloes
    0.39
     halos
    0.39
    Sn
    0.37
     mound
    0.36
     mente
    0.36
     hect
    0.35
    plat
    0.35
     HLA
    0.35
    protractor
    0.34
    AYLOR
    0.34
    Activations Density 0.000%

    No Known Activations