© 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. 60415
    Prev
    Next
    INDEX
    Explanations

    specific numbers and dates

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

    answering questions or giving instructions

    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
    哃
    0.52
    籹
    0.47
     مليار
    0.47
    籵
    0.46
     نص
    0.46
     Lipid
    0.45
    泍
    0.45
     فار
    0.43
    缁
    0.43
     पस
    0.43
    POSITIVE LOGITS
    asana
    0.55
     agosto
    0.49
     honti
    0.47
    zco
    0.47
    archivo
    0.47
    arduino
    0.46
    dato
    0.46
     everywhere
    0.45
    דע
    0.44
    diamonds
    0.44
    Activations Density 0.000%

    No Known Activations