© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39704
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and identifiers

    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
     from
    -1.12
     that
    -0.96
    rater
    -0.93
     przód
    -0.93
     предполага
    -0.93
    xty
    -0.91
    even
    -0.91
     postale
    -0.89
     password
    -0.88
    ♎
    -0.87
    POSITIVE LOGITS
    Ingrediente
    0.94
    arbitrary
    0.93
    Bibliografie
    0.92
     같은
    0.91
    AppMethod
    0.88
    Aplica
    0.88
    merkungen
    0.84
    Caracter
    0.84
     titans
    0.84
    hatenablog
    0.84
    Activations Density 0.007%

    No Known Activations