© 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. 65560
    Prev
    Next
    INDEX
    Explanations

    celebrating Marketing, Day, resected

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

    HUGE and

    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
     Robots
    0.50
     Theresa
    0.49
    nobody
    0.46
     pessoa
    0.45
     Ritual
    0.45
     Alex
    0.45
    闱
    0.44
    াল
    0.44
     Runs
    0.43
     juridique
    0.43
    POSITIVE LOGITS
     abiotic
    0.48
    හාර
    0.47
     hatch
    0.47
     выдви
    0.46
    ripción
    0.46
    នុ
    0.46
    alakip
    0.45
     macron
    0.44
    hattisgarh
    0.44
    %);
    0.43
    Activations Density 0.002%

    No Known Activations