© 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. 217194
    Prev
    Next
    INDEX
    Explanations

    observe body, leader or, fully condition, first step, early market

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

    explaining likelihood and sensory details

    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
    ამაშ
    0.58
     Superintend
    0.52
     Federer
    0.52
    গতকাল
    0.51
    㓈
    0.51
     Merced
    0.48
    വരെ
    0.48
    ਸ਼
    0.48
     बैंकिंग
    0.48
    राष्ट्रपति
    0.47
    POSITIVE LOGITS
     knotted
    0.48
    .
    0.48
     coarsely
    0.47
     ui
    0.47
     lighted
    0.46
     tactile
    0.46
     waxed
    0.45
     painted
    0.45
     sensorial
    0.45
    /
    0.44
    Activations Density 0.001%

    No Known Activations