© 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. 10-GEMMASCOPE-RES-131K
    7. 48408
    Prev
    Next
    INDEX
    Explanations

    real-time

    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_10/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
    a
    -3.02
     to
    -2.50
    i
    -2.39
    "])
    -2.38
    ڧ
    -2.31
    ～。
    -2.27
     comprising
    -2.14
    い
    -2.13
     until
    -2.11
    }}}
    -2.05
    POSITIVE LOGITS
    翃
    3.05
     uncompromising
    2.83
     impec
    2.69
     unquestion
    2.64
    IN
    2.63
     enchanting
    2.63
     renowned
    2.55
     kimdir
    2.52
     alluring
    2.50
     booming
    2.48
    Activations Density 0.009%

    No Known Activations