© 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. 44524
    Prev
    Next
    INDEX
    Explanations

    organization names and 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
    -
    -1.34
     some
    -1.19
     all
    -1.15
     cewek
    -1.10
    擔
    -1.09
    的速度
    -1.07
    AppCompatTheme
    -1.06
     selatan
    -1.06
    嚮
    -1.05
    ón
    -1.05
    POSITIVE LOGITS
     jego
    1.46
     onPostExecute
    1.42
    鸨
    1.36
    ковка
    1.35
     onOptions
    1.34
     após
    1.34
    imágenes
    1.30
    Esperamos
    1.30
    」、
    1.29
    función
    1.29
    Activations Density 0.373%

    No Known Activations