© 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. 53286
    Prev
    Next
    INDEX
    Explanations

    foreign names followed by said

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

    example handling

    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
    䁂
    0.46
     motivation
    0.43
    ived
    0.43
    ighter
    0.42
     подготовки
    0.41
    unding
    0.40
    ೊ
    0.40
    㽚
    0.40
    idents
    0.39
    毎回
    0.39
    POSITIVE LOGITS
     อื่น
    0.48
     ancienne
    0.47
    の人
    0.47
     από
    0.46
    ออกจาก
    0.45
    θεί
    0.45
    कारों
    0.45
     România
    0.45
     deixou
    0.45
     చిన్న
    0.45
    Activations Density 0.000%

    No Known Activations