© 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. 84782
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    殇
    -1.57
    賑
    -1.48
     including
    -1.45
     akin
    -1.38
     pungkasnya
    -1.34
     like
    -1.31
     diversa
    -1.31
     інших
    -1.30
     seems
    -1.30
     delas
    -1.30
    POSITIVE LOGITS
    roon
    1.45
     ọ
    1.42
    mathrm
    1.41
     nje
    1.40
     publik
    1.38
     منز
    1.38
    éd
    1.37
    itzende
    1.34
     lakini
    1.34
    äste
    1.33
    Activations Density 0.072%

    No Known Activations