© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65923
    Prev
    Next
    INDEX
    Explanations

    namespace.path.file

    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
     okno
    -1.44
    któ
    -1.43
     jednod
    -1.33
    の方も
    -1.30
    مبر
    -1.30
    になりたい
    -1.28
    感じで
    -1.23
     stroj
    -1.21
     biela
    -1.16
     their
    -1.16
    POSITIVE LOGITS
    y
    1.52
    an
    1.52
    a
    1.48
    h
    1.41
    b
    1.36
    is
    1.35
    u
    1.35
    i
    1.34
    me
    1.30
    j
    1.30
    Activations Density 0.036%

    No Known Activations