© 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. 142218
    Prev
    Next
    INDEX
    Explanations

    idea that

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

    However followed by disclaimer

    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
     রয়েছে
    0.54
     Tach
    0.51
    類
    0.50
     stwier
    0.49
    澳洲
    0.49
    戰爭
    0.47
    生態
    0.47
     वर्णन
    0.47
    ताना
    0.46
     avem
    0.46
    POSITIVE LOGITS
    י
    0.48
    Input
    0.47
    gherita
    0.47
    Shortly
    0.47
    н
    0.47
    quickly
    0.46
    Sprite
    0.45
    +#+#
    0.45
    以免
    0.45
    سمبر
    0.44
    Activations Density 0.001%

    No Known Activations