© 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. 73646
    Prev
    Next
    INDEX
    Explanations

    books and reading

    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
     vpon
    -1.39
     verantwortlich
    -1.26
     operating
    -1.19
     useful
    -1.16
    狀況
    -1.12
    月中旬
    -1.12
     größer
    -1.09
    儼
    -1.09
     desired
    -1.09
     nodig
    -1.05
    POSITIVE LOGITS
    𝘼
    1.32
     Obtener
    1.31
     irmão
    1.24
    𝙰
    1.24
    Además
    1.21
     morceau
    1.21
    (!__
    1.20
     Crear
    1.20
    ypen
    1.20
    äsenti
    1.16
    Activations Density 0.115%

    No Known Activations