© 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. 65111
    Prev
    Next
    INDEX
    Explanations

    questions and configurations

    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
     of
    -1.65
     what
    -1.30
     all
    -1.27
     by
    -1.16
     problems
    -1.11
    laise
    -1.09
     results
    -1.05
     históricos
    -1.05
     $
    -1.03
     здания
    -1.03
    POSITIVE LOGITS
     and
    1.33
    Ꮠ
    1.20
     vuelos
    1.16
    Fonto
    1.14
     nadru
    1.14
     verborgen
    1.13
    potranspiration
    1.12
    дәбият
    1.12
    haden
    1.12
     atteindre
    1.11
    Activations Density 0.000%

    No Known Activations