© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73200
    Prev
    Next
    INDEX
    Explanations

    Odoo Server, Q:, Amaz, All, Field

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ност
    -1.34
    ꞈ
    -1.17
     STILL
    -1.16
    atzes
    -1.13
     广告
    -1.13
    Она
    -1.12
     női
    -1.12
     alkot
    -1.12
     England
    -1.11
     微信
    -1.10
    POSITIVE LOGITS
     their
    1.32
     requerida
    1.28
    原始内容
    1.09
    、
    1.09
    actoring
    1.07
    logeny
    1.05
    ⠄
    1.05
    Fonto
    1.05
     взрослых
    1.04
     fonctions
    1.03
    Activations Density 0.016%

    No Known Activations