© 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. 65002
    Prev
    Next
    INDEX
    Explanations

    enum and choices

    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
    kritik
    -0.94
    suz
    -0.90
     IAAF
    -0.87
     ſame
    -0.87
     bakteri
    -0.86
    ныхъ
    -0.85
    ށ
    -0.84
    ἃ
    -0.84
    Всем
    -0.84
     interessa
    -0.84
    POSITIVE LOGITS
     choices
    1.26
     choosing
    1.14
     either
    1.09
     various
    1.05
     choice
    1.04
    choices
    1.03
    Enum
    1.02
     options
    1.01
     selecting
    0.99
     deciding
    0.96
    Activations Density 0.017%

    No Known Activations