© 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. 186391
    Prev
    Next
    INDEX
    Explanations

    legally problematic, infringing rights, contracts

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

    creation of the world

    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
     cierto
    0.46
    إ
    0.42
     oxygen
    0.42
     chromosomal
    0.42
    问
    0.42
    增长
    0.41
     HPV
    0.41
    艺
    0.41
     آدم
    0.41
    检查
    0.40
    POSITIVE LOGITS
    FEM
    0.50
    IL
    0.49
    UH
    0.48
    BK
    0.48
    perties
    0.48
    FRINGEMENT
    0.47
    ET
    0.46
    yllic
    0.46
     ভু
    0.46
    UD
    0.46
    Activations Density 0.000%

    No Known Activations