© 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. 9495
    Prev
    Next
    INDEX
    Explanations

    suggests that

    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
    crania
    -1.16
     terlihat
    -1.15
    čky
    -1.15
     parecía
    -1.14
    )²
    -1.13
    )$,
    -1.13
     aquellos
    -1.13
    ：【
    -1.13
     podrán
    -1.13
     acontecer
    -1.12
    POSITIVE LOGITS
     not
    1.41
     beeinflussen
    1.27
     betreffende
    1.24
    addWidget
    1.23
     then
    1.23
    他的
    1.20
    
    1.18
     puis
    1.17
    -
    1.16
     now
    1.15
    Activations Density 0.099%

    No Known Activations