© 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. 240240
    Prev
    Next
    INDEX
    Explanations

    onboard credential aged bond

    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
     baixo
    0.48
    вок
    0.46
    ็ม
    0.46
    pectral
    0.46
     ڈاؤن
    0.45
    คโนโล
    0.45
    ی
    0.45
    ço
    0.44
    грамма
    0.43
     ağı
    0.43
    POSITIVE LOGITS
     caseworker
    0.53
     सालाना
    0.52
    inam
    0.50
     kojim
    0.50
     結婚
    0.50
     যেটি
    0.49
     或者
    0.49
     जिसके
    0.48
     Конечно
    0.48
     將
    0.47
    Activations Density 0.000%

    No Known Activations