© 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. 10-GEMMASCOPE-RES-131K
    7. 103837
    Prev
    Next
    INDEX
    Explanations

    Tchaikovsky concertos or CharSequence

    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
    </strong>
    -2.33
    \
    -2.13
     was
    -2.13
    IN
    -2.09
     underwhelming
    -1.98
    }$
    -1.97
     unab
    -1.95
    "
    -1.88
     heartwarming
    -1.80
    (
    -1.80
    POSITIVE LOGITS
    鸝
    2.31
    งิน
    2.14
     WHICH
    2.14
     untuk
    2.06
    鱨
    1.99
    が必要です
    1.97
    阄
    1.96
    </h5>
    1.90
     Empfang
    1.90
    
    1.88
    Activations Density 0.000%

    No Known Activations