© 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. 18025
    Prev
    Next
    INDEX
    Explanations

    Stunning iMac iPhones

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

    lists of options

    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
    ポ
    0.55
    ệng
    0.47
     цих
    0.47
     diva
    0.46
    нии
    0.45
     betreff
    0.45
    ู
    0.45
     கடவு
    0.45
     seyd
    0.44
    guru
    0.43
    POSITIVE LOGITS
     ఇప్పటికే
    0.52
     iMac
    0.49
     propiedades
    0.47
    ainless
    0.46
     Stunning
    0.46
     iPhones
    0.45
     ℝ
    0.45
     María
    0.45
     Pyrénées
    0.45
     بحث
    0.45
    Activations Density 0.000%

    No Known Activations