© 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. 45108
    Prev
    Next
    INDEX
    Explanations

    all important

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

    competitive landscape

    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
    Elemental
    0.44
     към
    0.43
    wey
    0.43
    ↵
    0.42
     aast
    0.41
    eda
    0.41
    letts
    0.41
    ὴν
    0.41
     discouraged
    0.41
    akuwa
    0.41
    POSITIVE LOGITS
     माहिती
    0.50
    StockDel
    0.50
     chapitre
    0.48
    iziModal
    0.48
    lymph
    0.47
    서비스
    0.46
    poem
    0.46
     پیام
    0.46
    𝓶
    0.46
    Gson
    0.45
    Activations Density 0.000%

    No Known Activations