© 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. 67178
    Prev
    Next
    INDEX
    Explanations

    high and low values

    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
     in
    -1.58
     kriminal
    -1.52
     laki
    -1.48
     kela
    -1.46
     penonton
    -1.42
     seksi
    -1.41
     贺
    -1.41
    They
    -1.37
     maksi
    -1.37
     luka
    -1.34
    POSITIVE LOGITS
    </u>
    1.83
     otros
    1.79
     любой
    1.66
    </h3>
    1.57
     dzies
    1.52
     également
    1.52
     bemerken
    1.52
     '
    1.51
    xiii
    1.50
     herab
    1.50
    Activations Density 0.036%

    No Known Activations