© 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. 53-GEMMASCOPE-2-RES-65K
    7. 7736
    Prev
    Next
    INDEX
    Explanations

    language and content management

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

    Sir Digsalot, SirSpamAlot, Podkrepi.bg, Mastodon

    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_53_width_65k_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
    ırlar
    0.42
    ället
    0.42
    ās
    0.41
     eğer
    0.40
    渍
    0.40
    经过
    0.40
    aları
    0.39
    马
    0.39
    alım
    0.39
     Eğer
    0.39
    POSITIVE LOGITS
    ถ
    0.59
    เท
    0.59
    ป
    0.59
    เ
    0.58
    ต
    0.54
    ข
    0.54
    การ
    0.52
    บริษัท
    0.52
     บริษัท
    0.52
    เดือน
    0.52
    Activations Density 0.001%

    No Known Activations