© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 0
    Prev
    Next
    INDEX
    Explanations

    Spring Security OAuth cloud

    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
    hmigung
    -1.37
    alberto
    -1.33
    woch
    -1.29
     humiliated
    -1.27
     that
    -1.27
     pourriez
    -1.23
     Kindes
    -1.20
    ieR
    -1.20
    </h2>
    -1.18
    tería
    -1.18
    POSITIVE LOGITS
    f
    1.28
    man
    1.23
    for
    1.23
    so
    1.22
    L
    1.21
    с
    1.20
    O
    1.20
    something
    1.19
    where
    1.18
    Seznam
    1.18
    Activations Density 0.001%

    No Known Activations