© 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. 143715
    Prev
    Next
    INDEX
    Explanations

    episodes write

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

    social isolation

    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
    哳
    0.54
    鸿
    0.48
    嘻
    0.46
    ว
    0.45
    ม
    0.45
    鸫
    0.45
    ા
    0.44
    堞
    0.43
    音が
    0.43
    ฟ
    0.43
    POSITIVE LOGITS
    0.54
     phytoplankton
    0.50
     replenished
    0.50
     guests
    0.49
     tariff
    0.49
     usable
    0.48
     dispensation
    0.47
     utilisation
    0.47
     delayed
    0.47
     paediatric
    0.47
    Activations Density 0.000%

    No Known Activations