© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 246015
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and roles

    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
     hız
    0.49
    ϛ
    0.48
     pręd
    0.46
     быстро
    0.46
     ıs
    0.46
     rápido
    0.45
     orderBy
    0.44
    ҳо
    0.43
     açıklam
    0.43
    失望
    0.42
    POSITIVE LOGITS
     کسی
    0.43
     כ
    0.43
    atein
    0.43
     সবাই
    0.41
     মস্তি
    0.41
    ahui
    0.40
     কারো
    0.40
     কাহারও
    0.40
    UKI
    0.40
    ChatItem
    0.40
    Activations Density 0.000%

    No Known Activations