© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 87729
    Prev
    Next
    INDEX
    Explanations

    parallel

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

    building blocks like LEGOs

    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
    مل
    0.53
    ى
    0.50
    გრ
    0.49
    بلا
    0.49
     vén
    0.49
     حيات
    0.47
    <0x93>
    0.46
     vidéo
    0.45
    카
    0.44
    غا
    0.44
    POSITIVE LOGITS
    EN
    0.60
    ENS
    0.51
    oproteins
    0.49
    instance
    0.46
     parlament
    0.46
    PT
    0.45
    are
    0.45
    GPS
    0.45
    discrete
    0.45
    acetone
    0.45
    Activations Density 0.001%

    No Known Activations