© 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. 127
    Prev
    Next
    INDEX
    Explanations

    I think, I ponder

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

    many, common, popular

    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
     đươ
    0.42
     saver
    0.40
     pă
    0.39
     அறிக
    0.39
    του
    0.39
    ΤΟ
    0.39
     esquema
    0.39
    薩
    0.39
    TLS
    0.38
     consulte
    0.38
    POSITIVE LOGITS
     गठित
    0.51
     groaned
    0.40
     रीजन
    0.40
     Continent
    0.39
    蛀
    0.38
    ército
    0.38
    受注
    0.38
     গঙ্গ
    0.38
    Dragging
    0.38
    вобо
    0.37
    Activations Density 0.000%

    No Known Activations