© 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. 10-GEMMASCOPE-RES-131K
    7. 45291
    Prev
    Next
    INDEX
    Explanations

    Whatever followed by various clauses

    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
    S
    -2.28
    c
    -2.09
    A
    -2.02
    E
    -2.02
    \
    -1.98
    b
    -1.97
    ca
    -1.97
    의
    -1.90
     giu
    -1.89
    </h2>
    -1.86
    POSITIVE LOGITS
     intricacies
    1.91
     És
    1.80
     Before
    1.80
    傀
    1.77
     mereka
    1.76
     Through
    1.75
    𝘁
    1.73
     Since
    1.71
     That
    1.68
     They
    1.67
    Activations Density 0.005%

    No Known Activations