© 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. 84650
    Prev
    Next
    INDEX
    Explanations

    prime example

    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
     today
    -1.34
    mathrm
    -1.34
    -
    -1.32
    itize
    -1.31
    want
    -1.30
    href
    -1.28
     Anſ
    -1.27
     ‘‘
    -1.26
    ᓚ
    -1.23
    immediately
    -1.22
    POSITIVE LOGITS
     who
    1.45
     could
    1.45
    </b>
    1.34
     klara
    1.30
     that
    1.30
    ⢧
    1.28
    ческом
    1.27
    ᓕ
    1.26
    Since
    1.25
     hemma
    1.23
    Activations Density 0.098%

    No Known Activations