© 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. 148472
    Prev
    Next
    INDEX
    Explanations

    safety rules and liability

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

    creative writing or fictional stories

    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
     chees
    0.50
     phones
    0.47
    σ
    0.47
    소
    0.46
     barbe
    0.45
     pizzas
    0.45
    प्रतिनि
    0.45
    ें
    0.43
     versa
    0.43
     octobre
    0.43
    POSITIVE LOGITS
     Society
    0.55
     Safety
    0.49
    🩺
    0.49
    وية
    0.49
    ו
    0.49
    ئیں۔
    0.49
    🦓
    0.49
     رکھتے
    0.48
     Keeping
    0.48
     Societies
    0.48
    Activations Density 0.001%

    No Known Activations