© 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. 179410
    Prev
    Next
    INDEX
    Explanations

    accepts these cards

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

    software development contexts

    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
    ablus
    0.47
     않아
    0.45
     ఖ
    0.44
    arbeitung
    0.44
    çamento
    0.44
     언
    0.43
     сравнению
    0.43
     상수
    0.43
     મા
    0.43
     համ
    0.43
    POSITIVE LOGITS
    بعد
    0.53
    tres
    0.50
     discour
    0.47
     Thun
    0.47
    鱧
    0.47
    After
    0.46
     tres
    0.46
     ร้าน
    0.46
     siano
    0.46
    ঠোর
    0.45
    Activations Density 0.001%

    No Known Activations