© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 25689
    Prev
    Next
    INDEX
    Explanations

    code definitions and structures

    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
    eſ
    -1.16
     هر
    -1.13
     mystérie
    -1.10
     adesivo
    -1.05
     évêque
    -1.04
     myster
    -1.03
    ebly
    -1.02
    鵙
    -1.00
    θεν
    -0.99
    ₘ
    -0.99
    POSITIVE LOGITS
     type
    1.14
     as
    1.14
     to
    1.07
     which
    1.05
     F
    1.02
     use
    1.01
     characteristics
    1.01
     in
    1.01
     can
    0.99
     on
    0.99
    Activations Density 0.024%

    No Known Activations