© 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. 151330
    Prev
    Next
    INDEX
    Explanations

    navigation menus

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

    May to October

    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
    looped
    0.44
    ը
    0.44
     সম্বন্ধ
    0.43
     переменных
    0.43
    瘓
    0.42
     развед
    0.41
    衮
    0.41
    衩
    0.41
    과의
    0.41
     छात्रा
    0.41
    POSITIVE LOGITS
     preferential
    0.48
     SCRI
    0.45
     tampoco
    0.43
     keng
    0.43
     tuvimos
    0.43
     documents
    0.42
     callus
    0.42
     nejsou
    0.42
     mayoral
    0.42
     narrow
    0.42
    Activations Density 0.001%

    No Known Activations