© 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. 128360
    Prev
    Next
    INDEX
    Explanations

    programming identifiers and syntax

    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
    為に
    -1.29
     of
    -1.28
     buhay
    -1.13
    conocimiento
    -1.11
     similaires
    -1.05
     tämä
    -1.05
     continuare
    -1.04
     Mr
    -1.02
     białe
    -1.02
     ibang
    -1.02
    POSITIVE LOGITS
    โอ
    1.13
    opley
    1.08
     fornic
    1.02
     Schrö
    1.00
     Prou
    0.99
     mav
    0.99
    但却
    0.99
    甕
    0.98
     الوزراء
    0.98
    lgica
    0.97
    Activations Density 0.004%

    No Known Activations