© 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. 70051
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and comparisons

    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
    </h2>
    -1.84
    </i>
    -1.57
     fourth
    -1.56
    </h3>
    -1.56
     contributo
    -1.53
     Rät
    -1.52
     немає
    -1.51
     materna
    -1.47
     stanga
    -1.45
     it
    -1.44
    POSITIVE LOGITS
    -
    1.64
    '
    1.63
    (!)
    1.48
     verhind
    1.45
     hebt
    1.38
     inauguración
    1.34
     reinigen
    1.34
     esimerkiksi
    1.32
     gekocht
    1.32
     correctes
    1.28
    Activations Density 0.015%

    No Known Activations