© 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. 66449
    Prev
    Next
    INDEX
    Explanations

    by means of

    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
    しちゃ
    -1.48
     fiabilidad
    -1.35
    してました
    -1.34
     durabilidad
    -1.31
    épar
    -1.30
    dalam
    -1.27
     Stretcher
    -1.26
     would
    -1.26
     obrazu
    -1.26
    軼
    -1.25
    POSITIVE LOGITS
     of
    2.52
     You
    1.73
    a
    1.70
    r
    1.61
    n
    1.59
    g
    1.51
    A
    1.48
    你也
    1.48
    b
    1.48
    on
    1.45
    Activations Density 0.032%

    No Known Activations