© 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. 45315
    Prev
    Next
    INDEX
    Explanations

    mash/mashup

    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
    ztes
    -2.52
     was
    -2.52
    </h3>
    -2.48
    .
    -2.44
    超越
    -2.36
     We
    -2.34
     doesn
    -2.30
    睃
    -2.27
    Ᏺ
    -2.25
    鶫
    -2.25
    POSITIVE LOGITS
    y
    2.64
    1
    2.45
    不斷
    2.41
    4
    2.38
     吳
    2.27
    </b>
    2.16
     當
    2.08
    Eight
    2.00
     遇
    1.99
     удовлет
    1.98
    Activations Density 0.002%

    No Known Activations