© 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. 11199
    Prev
    Next
    INDEX
    Explanations

    programming code identifiers

    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
    기도
    -1.20
    ꉂ
    -1.15
     burada
    -1.13
    Specifik
    -1.12
    Podemos
    -1.11
    Stap
    -1.04
    Quando
    -1.02
     fidé
    -1.01
     circumstantial
    -1.00
     einzelnen
    -1.00
    POSITIVE LOGITS
    ⬯
    1.17
    D
    1.09
     able
    1.09
    T
    1.09
     wyda
    1.06
     done
    1.04
     Մ
    1.03
     bosques
    1.03
     perguntou
    1.02
     senza
    1.00
    Activations Density 0.004%

    No Known Activations