© 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. 44983
    Prev
    Next
    INDEX
    Explanations

    numbers and data types

    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
    .”
    -1.41
    ętr
    -1.34
    no
    -1.24
    puted
    -1.24
     TESTS
    -1.22
    mu
    -1.18
     الفنان
    -1.18
    …”
    -1.15
    in
    -1.14
     شهرد
    -1.14
    POSITIVE LOGITS
     fördern
    1.41
     Beschluss
    1.38
     When
    1.38
     Когда
    1.37
     tästä
    1.31
     ausdrück
    1.30
    FormBuilder
    1.30
     stärken
    1.30
    água
    1.28
    jük
    1.27
    Activations Density 0.027%

    No Known Activations