© 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. 112097
    Prev
    Next
    INDEX
    Explanations

    monthly reports, bio, photos, brand

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

    integrated applications

    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
    ຊ
    0.51
     virtu
    0.49
     wonders
    0.45
    ز
    0.45
     actu
    0.43
     axe
    0.43
     lawsuits
    0.43
    โครงการ
    0.43
     studi
    0.42
     outwardly
    0.42
    POSITIVE LOGITS
    arlo
    0.52
    ောင့်
    0.50
    arci
    0.49
     অনিশ্চ
    0.48
     conseils
    0.48
    桃
    0.46
     Needs
    0.46
     descanso
    0.46
    ریق
    0.45
    termination
    0.45
    Activations Density 0.005%

    No Known Activations