© 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. 39002
    Prev
    Next
    INDEX
    Explanations

    commit metadata dates

    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
    }
    -2.00
    很多
    -1.84
     this
    -1.84
     if
    -1.74
     was
    -1.59
    cję
    -1.57
     також
    -1.53
    after
    -1.48
     should
    -1.46
     because
    -1.46
    POSITIVE LOGITS
    Vlast
    1.64
     presentará
    1.56
     invitar
    1.54
     sorprender
    1.52
    摆手
    1.49
    句話
    1.48
    Beskrivelse
    1.45
    0
    1.45
     vnnd
    1.42
     preguntar
    1.42
    Activations Density 0.002%

    No Known Activations