© 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. 71848
    Prev
    Next
    INDEX
    Explanations

    entity framework

    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
    9
    -2.86
    if
    -2.72
    a
    -2.56
    1
    -2.52
    2
    -2.50
    3
    -2.47
    8
    -2.45
     You
    -2.41
    5
    -2.36
    ase
    -2.28
    POSITIVE LOGITS
    Ꮉ
    2.88
    诹
    2.86
    沇
    2.80
    賡
    2.52
     शुर
    2.48
    洨
    2.39
    fated
    2.36
    迨
    2.31
    ࿙
    2.31
    于是
    2.31
    Activations Density 0.011%

    No Known Activations