© 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. 191673
    Prev
    Next
    INDEX
    Explanations

    firstly, family, services, technology

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

    simple choices

    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
     complète
    0.56
    та
    0.50
    нд
    0.50
    ẫu
    0.48
    笂
    0.46
    tn
    0.45
    getFocus
    0.45
    óz
    0.44
     +
    0.44
    лд
    0.44
    POSITIVE LOGITS
     порядку
    0.49
     (…)
    0.49
     viktigt
    0.47
     lakini
    0.46
     юриди
    0.45
     aquele
    0.45
     exatamente
    0.45
    道理
    0.45
     אבל
    0.44
    !”,
    0.44
    Activations Density 0.001%

    No Known Activations