© 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. 175585
    Prev
    Next
    INDEX
    Explanations

    fried bean, skinned instructor

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

    property, stress, jars, duty

    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
    を中心
    0.49
     কেন্দ
    0.48
     центром
    0.47
     Verantwort
    0.46
    撷
    0.43
    Selected
    0.43
    Elect
    0.43
    ங்களாக
    0.43
    া
    0.42
    Revolution
    0.42
    POSITIVE LOGITS
     ดู
    0.54
     tree
    0.48
     caver
    0.45
     hermosa
    0.45
     lombok
    0.45
    izó
    0.45
    กา
    0.45
     LOGGER
    0.45
     permite
    0.44
     ByteBuffer
    0.44
    Activations Density 0.001%

    No Known Activations