© 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. 226149
    Prev
    Next
    INDEX
    Explanations

    Fisher, spirit, vegetable, chasing, vent

    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
     Principe
    0.52
    帶
    0.48
     URANIUM
    0.48
    櫻
    0.48
     Rxb
    0.47
    ные
    0.47
     Prinzip
    0.47
     Elkus
    0.47
    際
    0.47
     Deals
    0.46
    POSITIVE LOGITS
    ku
    0.52
    ontology
    0.47
    enti
    0.46
    이고
    0.46
    odi
    0.45
     contrasts
    0.45
    jes
    0.45
    ming
    0.44
    ows
    0.44
    uku
    0.43
    Activations Density 0.002%

    No Known Activations