© 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. 72744
    Prev
    Next
    INDEX
    Explanations

    prefix of code or documentation

    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
     their
    -1.29
     devez
    -1.13
     vya
    -1.09
     hjemmeside
    -1.05
     tigre
    -1.04
    erschied
    -1.03
     povezave
    -1.03
     santai
    -1.01
     kontin
    -1.00
    Ѕ
    -0.97
    POSITIVE LOGITS
     obicei
    1.06
     Vereinbarung
    1.03
     notwendi
    1.03
     abaixo
    1.00
    excellents
    1.00
     Hinsicht
    0.98
     jednak
    0.97
     deoarece
    0.96
    差別
    0.96
     proposta
    0.96
    Activations Density 0.001%

    No Known Activations