© 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. 160759
    Prev
    Next
    INDEX
    Explanations

    numbers and specific words

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

    Baltic Sea documentation

    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
     vínculo
    0.52
    mediately
    0.48
     乳
    0.47
    楔
    0.46
     た
    0.46
     мани
    0.45
     failures
    0.45
     ಮನೆ
    0.45
     ఉన్నాయి
    0.44
     त्वरित
    0.44
    POSITIVE LOGITS
    ✈
    0.45
    ند
    0.44
    ⌛
    0.44
    ⏳
    0.41
    withId
    0.40
    ষ্ট
    0.40
    댈
    0.40
    🏟
    0.39
    placeholder
    0.38
    星球
    0.38
    Activations Density 0.000%

    No Known Activations