© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9864
    Prev
    Next
    INDEX
    Explanations

    Read more

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

    code blocks or structured data

    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_40_width_16k_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
    IAC
    0.44
    กา
    0.43
    ICAN
    0.43
     OPTIONS
    0.42
    :`
    0.41
    facilities
    0.41
    OPTIONS
    0.40
     encapsulated
    0.40
    adjustment
    0.39
    Options
    0.38
    POSITIVE LOGITS
     Show
    0.59
     [+]
    0.59
     Mostrar
    0.58
     [+
    0.57
     อ่าน
    0.56
     Daha
    0.54
     Voir
    0.53
     zob
    0.53
     Xem
    0.53
     Lihat
    0.52
    Activations Density 0.043%

    No Known Activations