© 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. 130278
    Prev
    Next
    INDEX
    Explanations

    state of function or quality

    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
     acolo
    -0.95
    Vik
    -0.94
    Alemania
    -0.93
    ТА
    -0.92
    Contato
    -0.91
    Phong
    -0.90
    ポール
    -0.90
     pâtes
    -0.89
    Minh
    -0.88
     vải
    -0.87
    POSITIVE LOGITS
     its
    1.29
     itself
    1.24
     function
    1.00
     fonction
    0.98
     chứa
    0.98
    itself
    0.95
    它
    0.94
     ALLOW
    0.92
     用于
    0.91
     permettant
    0.91
    Activations Density 0.120%

    No Known Activations