© 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. 242901
    Prev
    Next
    INDEX
    Explanations

    safety in mind

    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
    √(
    0.59
    igraf
    0.55
    に入れる
    0.53
     reluctantly
    0.48
    qc
    0.46
    សម្
    0.46
    oprop
    0.45
    rätt
    0.45
     ત્યારબાદ
    0.45
     означа
    0.45
    POSITIVE LOGITS
    ↵
    0.59
    станции
    0.51
    فاوت
    0.50
     Portable
    0.48
     PackageManager
    0.47
    प्रतिनि
    0.46
     switcher
    0.46
     collections
    0.45
    环保
    0.45
     Routed
    0.45
    Activations Density 0.000%

    No Known Activations