© 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. 73192
    Prev
    Next
    INDEX
    Explanations

    not sure/exactly/feeling

    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
    {
    -2.38
     notwendig
    -1.85
    </h3>
    -1.83
     Surely
    -1.82
     Kontexten
    -1.80
     ponieważ
    -1.80
    </strong>
    -1.78
     Apparently
    -1.77
     With
    -1.76
     Nonetheless
    -1.76
    POSITIVE LOGITS
    檍
    2.08
    壆
    2.03
    Ꭳ
    2.00
     ekos
    1.95
    k
    1.91
    the
    1.89
    protein
    1.88
    ——”
    1.84
    hygiène
    1.84
     brû
    1.84
    Activations Density 0.014%

    No Known Activations