© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14229
    Prev
    Next
    INDEX
    Explanations

    NY codes

    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
    роятно
    -0.93
    を除
    -0.90
     THEIR
    -0.88
     adhesivo
    -0.83
     estekak
    -0.83
    ІІ
    -0.82
    🙉
    -0.82
     méxico
    -0.81
    ющи
    -0.80
    轻轻
    -0.80
    POSITIVE LOGITS
    ⊨
    0.99
    ską
    0.96
    などを
    0.94
     example
    0.94
     say
    0.92
     например
    0.91
     aspetti
    0.88
    Gpio
    0.85
     ejemplo
    0.84
     collezione
    0.83
    Activations Density 0.007%

    No Known Activations