© 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. 98240
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical explanations

    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
     castel
    -1.34
     it
    -1.28
     fasc
    -1.27
     Oriente
    -1.20
     carnaval
    -1.20
     destina
    -1.18
    konos
    -1.18
     alcool
    -1.17
     faſt
    -1.17
     grati
    -1.16
    POSITIVE LOGITS
     reforzar
    1.16
     simplesmente
    1.12
    TacToe
    1.12
     disponer
    1.12
     amortecedor
    1.10
     invitaciones
    1.09
     farbe
    1.09
     apont
    1.08
    THERE
    1.07
     simply
    1.06
    Activations Density 0.002%

    No Known Activations