© 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. 53299
    Prev
    Next
    INDEX
    Explanations

    invitation, ability, advent, play, older

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

    IP addresses and numbers

    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
    鐺
    0.49
     áll
    0.49
    gina
    0.48
    EDED
    0.47
     allons
    0.45
    你也
    0.45
    你們
    0.44
    гина
    0.43
    第一個
    0.43
    賁
    0.43
    POSITIVE LOGITS
     Any
    0.44
    ere
    0.39
     Goodrich
    0.39
     Causeway
    0.39
    erto
    0.39
     Store
    0.39
    urned
    0.38
    elho
    0.38
     средней
    0.38
     Such
    0.38
    Activations Density 0.002%

    No Known Activations