© 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. 73317
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

    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
    ゚
    -1.30
    ）　
    -0.99
    metrie
    -0.96
    撰文
    -0.92
     CITED
    -0.90
    וּ
    -0.89
    pecified
    -0.89
     TMPro
    -0.88
    こんばんは
    -0.87
     drago
    -0.86
    POSITIVE LOGITS
    opathology
    1.09
    italien
    1.07
     studies
    1.02
     oyuncak
    1.01
     Verkaufs
    1.00
    していますが
    0.97
     cukru
    0.96
     Fassung
    0.96
     uncomfortable
    0.96
     amazing
    0.96
    Activations Density 0.070%

    No Known Activations