© 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. 38971
    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
     IndexPath
    -1.26
    J
    -1.19
    h
    -1.19
    B
    -1.17
    ↵↵
    -1.16
    L
    -1.13
    N
    -1.13
    v
    -1.11
    g
    -1.11
    t
    -1.11
    POSITIVE LOGITS
    Londres
    1.14
    这一次
    1.13
    ouac
    1.11
     magnético
    1.07
    makebox
    1.04
    Lucie
    1.04
    ڱ
    1.03
     cantantes
    1.02
    今後も
    1.02
    bánh
    1.02
    Activations Density 0.005%

    No Known Activations