© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43252
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

    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
     of
    -1.56
     it
    -1.51
     dibanding
    -1.27
    这里是
    -1.26
    This
    -1.26
    </tr>
    -1.20
     liik
    -1.20
    Sebelumnya
    -1.19
     Но
    -1.18
     miró
    -1.18
    POSITIVE LOGITS
     to
    1.79
     Gestión
    1.56
     beliebtesten
    1.43
     Diputados
    1.43
     PRICES
    1.38
    Ibid
    1.33
    凝土
    1.32
     EMPLOYEES
    1.30
     risultato
    1.30
    yacht
    1.28
    Activations Density 0.034%

    No Known Activations