© 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. 73979
    Prev
    Next
    INDEX
    Explanations

    deep followed by descriptive words

    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
    >
    -2.50
     This
    -2.33
     Another
    -2.30
     he
    -1.94
     Other
    -1.91
     to
    -1.90
    ྜ
    -1.89
     These
    -1.86
     Versuche
    -1.81
     somewhat
    -1.79
    POSITIVE LOGITS
    ଝ
    1.98
     menú
    1.88
    そういえば
    1.86
    >--}}
    1.86
    次は
    1.85
     یا
    1.84
    元々
    1.80
    鋮
    1.80
     که
    1.77
    こちらが
    1.76
    Activations Density 0.015%

    No Known Activations