© 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. 73032
    Prev
    Next
    INDEX
    Explanations

    programming code keywords

    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
    ɷ
    -1.55
     対策
    -1.54
    zji
    -1.52
    倬
    -1.52
     nestled
    -1.51
    zja
    -1.50
     入っ
    -1.48
    años
    -1.45
     oppervlak
    -1.45
     ligiloj
    -1.41
    POSITIVE LOGITS
    ’
    2.19
    d
    2.14
    c
    2.08
    8
    1.93
    le
    1.78
    te
    1.77
    _
    1.73
    3
    1.71
    g
    1.71
     con
    1.71
    Activations Density 0.008%

    No Known Activations