© 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. 241689
    Prev
    Next
    INDEX
    Explanations

    abrasion rubber, body negative

    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
    ன்
    0.59
    ት
    0.49
    지
    0.49
     Bors
    0.48
     Hammers
    0.47
     Opie
    0.47
     Sykes
    0.46
    ീ
    0.46
    엇
    0.45
     Archie
    0.45
    POSITIVE LOGITS
     адам
    0.48
     исследование
    0.48
     hạ
    0.47
    orrh
    0.46
    lında
    0.45
     জানেন
    0.45
     bottomRight
    0.44
    ibration
    0.43
    ilon
    0.43
    ibrated
    0.43
    Activations Density 0.001%

    No Known Activations