© 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. 10805
    Prev
    Next
    INDEX
    Explanations

    evicted from

    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
    ar
    -2.86
    ⸰
    -2.72
    袛
    -2.64
    over
    -2.52
    ”
    -2.50
    櫚
    -2.50
    艄
    -2.44
    man
    -2.39
     asin
    -2.38
    in
    -2.34
    POSITIVE LOGITS
     you
    3.20
     What
    2.55
     We
    2.55
     cuidadosamente
    2.55
     cómod
    2.52
     longtime
    2.44
    ⃙
    2.41
     aguj
    2.39
     hacer
    2.38
     These
    2.33
    Activations Density 0.001%

    No Known Activations