© 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. 158343
    Prev
    Next
    INDEX
    Explanations

    travel abroad

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

    defining concepts and categories

    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
    🈺
    0.51
    🏜
    0.48
    спублі
    0.44
    izioni
    0.44
     proclaimed
    0.42
    📤
    0.42
     дов
    0.41
    elsior
    0.41
     характер
    0.41
    🇬
    0.41
    POSITIVE LOGITS
     Example
    0.57
    ROTATE
    0.55
    rotate
    0.53
     rotate
    0.52
     CLASS
    0.50
    CLASS
    0.50
     Rotate
    0.49
     SPC
    0.49
    fear
    0.48
    体
    0.48
    Activations Density 0.000%

    No Known Activations