© 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. 83028
    Prev
    Next
    INDEX
    Explanations

    product model numbers

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

    model version tag

    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
    एमपी
    0.50
    라인
    0.43
    สามารถ
    0.42
    ӵ
    0.42
    ائر
    0.42
    attività
    0.42
    嗪
    0.42
     निशाना
    0.41
     ಇದರಿಂದ
    0.41
    ᖃ
    0.41
    POSITIVE LOGITS
     model
    0.82
    model
    0.71
    模型
    0.70
     модель
    0.69
     模型
    0.69
     modelo
    0.67
     modell
    0.67
     Model
    0.66
    Model
    0.65
     MODEL
    0.64
    Activations Density 0.000%

    No Known Activations