© 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. 169358
    Prev
    Next
    INDEX
    Explanations

    comparing entities or listing types

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

    writing and language use

    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
    рье
    0.54
    원은
    0.53
     rutina
    0.50
    وتي
    0.50
     únicamente
    0.49
     तीसरी
    0.48
     liderazgo
    0.47
    劑
    0.47
    褛
    0.47
    粦
    0.46
    POSITIVE LOGITS
    সংখ্যক
    0.49
     synagogue
    0.46
     grasped
    0.45
     collaborative
    0.45
     grasp
    0.44
     creatives
    0.44
     Water
    0.43
     words
    0.43
    <start_of_image>
    0.43
     creative
    0.43
    Activations Density 0.000%

    No Known Activations