© 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. 35089
    Prev
    Next
    INDEX
    Explanations

    java package components

    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
     tristes
    -1.60
    谞
    -1.59
     quedará
    -1.55
     podrob
    -1.55
     niektor
    -1.55
     ۱۱
    -1.55
     ۱۰
    -1.51
     murió
    -1.50
    ledad
    -1.50
    ⛦
    -1.49
    POSITIVE LOGITS
    N
    1.93
    M
    1.86
    C
    1.84
    G
    1.81
    ↵↵
    1.78
    B
    1.77
    L
    1.76
    O
    1.73
    U
    1.72
    1.71
    Activations Density 0.036%
    No Known Activations