© 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. 187627
    Prev
    Next
    INDEX
    Explanations

    looking for We

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

    group aims states auditing

    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
     Republic
    0.44
     Automated
    0.44
    λώ
    0.42
    ائ
    0.41
     Formula
    0.41
    ած
    0.41
     Migrate
    0.41
    鍏
    0.40
     Skill
    0.40
    偿
    0.40
    POSITIVE LOGITS
     בח
    0.54
     astrocyte
    0.52
    ऑक्साइड
    0.48
     ഓ
    0.47
     поха
    0.47
     repercussions
    0.46
     อยาก
    0.46
     acidity
    0.46
    列
    0.46
     업데이트
    0.46
    Activations Density 0.002%

    No Known Activations