© 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. 21124
    Prev
    Next
    INDEX
    Explanations

    now can do

    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
     a
    -2.33
    刳
    -1.36
     recente
    -1.28
    ggings
    -1.26
     siempre
    -1.26
     όμως
    -1.26
    ipts
    -1.25
     privil
    -1.23
     vacía
    -1.23
    ⛧
    -1.22
    POSITIVE LOGITS
     aproximativ
    1.51
     barnen
    1.34
     and
    1.33
    就可以
    1.30
     världen
    1.30
     början
    1.29
    妡
    1.23
     torsdag
    1.21
    h
    1.21
    ing
    1.20
    Activations Density 0.051%

    No Known Activations