© 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. 220605
    Prev
    Next
    INDEX
    Explanations

    travel

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

    connections fail

    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
    ುವ
    0.49
     বরিশ
    0.47
     sintomas
    0.46
     हमरे
    0.46
    ঵
    0.46
    ल्ल्या
    0.45
     Kharkiv
    0.44
    偪
    0.44
     aiuta
    0.43
     Educa
    0.43
    POSITIVE LOGITS
     assemblies
    0.51
     commonwealth
    0.50
    gene
    0.48
     dearth
    0.47
     stockpile
    0.45
     paucity
    0.45
     assembly
    0.45
     compound
    0.44
    Compound
    0.44
    ying
    0.44
    Activations Density 0.002%

    No Known Activations