© 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. 53658
    Prev
    Next
    INDEX
    Explanations

    eighth Wimbledon victory

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

    mom joke

    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
     가서
    0.46
     adsorbed
    0.44
     [
    0.44
     लगती
    0.44
     대해
    0.43
     GIF
    0.42
    NAMES
    0.42
     段
    0.42
     cloudy
    0.42
     માટે
    0.41
    POSITIVE LOGITS
     tourisme
    0.44
     caméra
    0.44
     treball
    0.44
    туре
    0.43
    ्त
    0.43
    緹
    0.43
     vys
    0.42
     travaille
    0.42
    طانیہ
    0.42
     نكمل
    0.42
    Activations Density 0.000%

    No Known Activations