© 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. 70443
    Prev
    Next
    INDEX
    Explanations

    theorem statements and proofs

    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
     \&
    -2.55
     was
    -2.34
    潆
    -2.27
     \#
    -2.19
    fromUtf
    -2.13
    。
    -2.13
    rician
    -2.08
    !!!!!!
    -2.08
    柒
    -2.08
    ?"
    -2.06
    POSITIVE LOGITS
    .
    4.00
    The
    2.55
    <i>
    2.38
    </i>
    2.34
     Schluß
    2.19
    桖
    2.16
    >
    2.16
     that
    1.98
     fondamental
    1.97
    人们
    1.95
    Activations Density 0.004%

    No Known Activations