© 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. 245848
    Prev
    Next
    INDEX
    Explanations

    written notice, no liability

    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
    atan
    0.50
    ţă
    0.49
    ີ່ມ
    0.47
    ishu
    0.47
    irlos
    0.46
     নিয়ম
    0.46
    洲
    0.46
    ünden
    0.46
    airlines
    0.46
    োগ্য
    0.45
    POSITIVE LOGITS
    ח
    0.47
    ت
    0.46
     described
    0.44
     electronic
    0.42
     faint
    0.42
     envoy
    0.42
     deems
    0.41
     собствен
    0.41
     descriptions
    0.41
     खुले
    0.41
    Activations Density 0.000%

    No Known Activations