© 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. 15865
    Prev
    Next
    INDEX
    Explanations

    titles of entities and roles

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

    screens, debug, edit, chemistry

    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
    冫
    0.54
    hcim
    0.47
    ᱘
    0.47
    টারের
    0.47
    msız
    0.46
     ಅವನು
    0.46
     কৌ
    0.46
    ෘ
    0.46
    yı
    0.45
    sız
    0.45
    POSITIVE LOGITS
     Screens
    0.53
     Screen
    0.50
     Hark
    0.47
     Chemie
    0.46
     screens
    0.46
     Ch
    0.45
     Debug
    0.45
    ármaz
    0.45
    ون
    0.45
     UIAlert
    0.45
    Activations Density 0.000%

    No Known Activations