© 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. 74961
    Prev
    Next
    INDEX
    Explanations

    celebrate Trump, for future

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

    fresh cheeses, raw, puzzle

    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
     または
    0.47
    łym
    0.45
     حلقه
    0.45
     問
    0.45
     confid
    0.44
     secrétaire
    0.44
     revital
    0.44
    nois
    0.44
     林
    0.43
     張
    0.43
    POSITIVE LOGITS
     Theft
    0.51
    Battery
    0.49
    Audio
    0.48
    Silver
    0.47
    for
    0.47
    Ether
    0.46
     பணிகள்
    0.46
    Vocabulary
    0.46
    க
    0.46
    Book
    0.45
    Activations Density 0.000%

    No Known Activations