© 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. 126444
    Prev
    Next
    INDEX
    Explanations

    testing is, safety and

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

    words in various contexts

    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
    立つ
    0.54
    бой
    0.52
    हां
    0.47
    庄
    0.46
    дер
    0.45
    лася
    0.45
    주의
    0.45
    শুর
    0.45
    Fla
    0.45
    sistema
    0.45
    POSITIVE LOGITS
     רק
    0.52
     τραγ
    0.49
     einzige
    0.48
     rutin
    0.47
     mortars
    0.46
     發
    0.46
     綿
    0.46
     lut
    0.45
     די
    0.44
     मुद्दे
    0.44
    Activations Density 0.001%

    No Known Activations