© 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. 133244
    Prev
    Next
    INDEX
    Explanations

    corresponding section, loans, Mattress, dream, overlook

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

    lists of items

    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
     acrylonitrile
    0.51
     avete
    0.48
     PWMB
    0.48
     hostilities
    0.46
     oov
    0.46
    ',
    0.46
    '`
    0.46
     amare
    0.46
     मोर्चा
    0.46
     nudity
    0.45
    POSITIVE LOGITS
    م
    0.49
    arschijnlijk
    0.46
    梦想
    0.44
    Ал
    0.44
    สร้าง
    0.43
     ა
    0.43
    강
    0.43
    Всем
    0.42
    ার্জ
    0.42
    项目
    0.42
    Activations Density 0.000%

    No Known Activations