© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36645
    Prev
    Next
    INDEX
    Explanations

    production and screenwriter

    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_22/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
     attempt
    -1.24
     Getränke
    -1.22
    cdot
    -1.18
     routine
    -1.18
     comunità
    -1.17
     thing
    -1.17
     günstiger
    -1.15
     people
    -1.13
     decoracion
    -1.13
     campionato
    -1.11
    POSITIVE LOGITS
    ପ
    1.48
     брюки
    1.36
     бампер
    1.30
    ᾽
    1.24
    骄
    1.20
    achable
    1.19
    苺
    1.19
     projet
    1.19
     sucre
    1.18
    闈
    1.17
    Activations Density 0.009%

    No Known Activations