© 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. 10-GEMMASCOPE-RES-131K
    7. 42324
    Prev
    Next
    INDEX
    Explanations

    improve your

    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
     Anhäng
    -1.19
     constamment
    -1.15
     (
    -1.15
     مثل
    -1.13
     дуже
    -1.10
    Nunca
    -1.09
     intende
    -1.09
     इत
    -1.08
    大人の
    -1.08
     nostro
    -1.08
    POSITIVE LOGITS
     they
    1.36
     serían
    1.26
    นน
    1.19
     funções
    1.19
    </tr>
    1.18
     Paweł
    1.17
    gráficas
    1.16
     kazi
    1.13
    είτε
    1.13
     what
    1.13
    Activations Density 0.036%

    No Known Activations