© 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. 155151
    Prev
    Next
    INDEX
    Explanations

    foreign words and specific nouns

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

    shocking things

    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
    ász
    0.47
    amentos
    0.45
     घटक
    0.44
     കൂടുതല്‍
    0.43
     Michaelmas
    0.43
    為什麼
    0.43
    ckel
    0.43
     鳥
    0.43
     друг
    0.42
    teros
    0.42
    POSITIVE LOGITS
    "</
    0.50
    েম্বরে
    0.49
    iennent
    0.49
    databases
    0.47
    soldiers
    0.47
    Rachel
    0.46
    Famil
    0.46
    诫
    0.46
     veulent
    0.46
    ។
    0.46
    Activations Density 0.001%

    No Known Activations