© 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. 100353
    Prev
    Next
    INDEX
    Explanations

    abstract

    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
     is
    -3.44
     \
    -3.20
    ,”
    -3.02
    </h4>
    -2.48
     новая
    -2.47
     ‘
    -2.44
    </b>
    -2.39
    नलोड
    -2.34
    !”
    -2.27
    н
    -2.22
    POSITIVE LOGITS
    騭
    2.63
    羕
    2.58
     abandonado
    2.45
     preferido
    2.44
     magnético
    2.44
    がっ
    2.36
    ￪
    2.34
     acento
    2.31
     importado
    2.27
    ひら
    2.27
    Activations Density 0.002%

    No Known Activations