© 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. 16049
    Prev
    Next
    INDEX
    Explanations

    code snippets 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
    ないです
    -0.93
    HStack
    -0.89
    race
    -0.85
    [!
    -0.82
     bụi
    -0.81
    example
    -0.81
    umia
    -0.79
    ேர
    -0.78
    ]]);
    -0.77
     destek
    -0.77
    POSITIVE LOGITS
     aquí
    0.80
    𝑶
    0.78
     Quarto
    0.78
    好評
    0.77
    缥
    0.76
     ніж
    0.76
    phrodite
    0.76
    謦
    0.75
     Hilfe
    0.75
     Years
    0.75
    Activations Density 0.019%

    No Known Activations