© 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. 8105
    Prev
    Next
    INDEX
    Explanations

    comic creators and works

    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
     Bezir
    -1.45
     když
    -1.33
    暧
    -1.32
     गर्न
    -1.32
    𝒙
    -1.30
     сказала
    -1.28
    đồ
    -1.27
     мечты
    -1.27
     ارزان
    -1.27
    绢
    -1.26
    POSITIVE LOGITS
    ɵɵelement
    1.52
     terceiro
    1.43
     freio
    1.42
    kusen
    1.32
    ṝ
    1.30
     espelho
    1.27
     ярма
    1.27
     pensamento
    1.25
     montaje
    1.25
    jekt
    1.25
    Activations Density 0.176%

    No Known Activations