© 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. 27421
    Prev
    Next
    INDEX
    Explanations

    symbols and separators

    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
     and
    -1.62
    の人は
    -1.08
    fällt
    -1.04
    HideInInspector
    -1.00
    äischen
    -0.99
    nyata
    -0.99
    atnya
    -0.98
    passwords
    -0.97
     This
    -0.97
     umana
    -0.96
    POSITIVE LOGITS
     două
    1.06
     lainnya
    1.05
     全新
    1.05
    without
    0.97
     官网
    0.92
     руке
    0.90
    过来了
    0.90
     饭
    0.90
     především
    0.89
    derived
    0.88
    Activations Density 0.051%

    No Known Activations