© 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. 113162
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific nouns

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

    action or state

    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
    g
    0.51
    迈
    0.46
     ejercicios
    0.46
    emples
    0.46
    acal
    0.45
     riforma
    0.45
    e
    0.45
    ,
    0.44
     holographic
    0.44
    a
    0.44
    POSITIVE LOGITS
     identifiable
    0.48
    РЕ
    0.48
     ವರ್ಗ
    0.46
     vždy
    0.46
    Наи
    0.45
     Наи
    0.45
    HEADERS
    0.45
     এজেন্ট
    0.44
    برى
    0.43
     ફરિયા
    0.43
    Activations Density 0.001%

    No Known Activations