© 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. 85701
    Prev
    Next
    INDEX
    Explanations

    there followed by location or state

    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
     is
    -1.96
     volontà
    -1.80
     dovr
    -1.79
     prossima
    -1.73
     terzo
    -1.67
     sarà
    -1.66
     żad
    -1.64
     incontra
    -1.59
     decisione
    -1.59
     привлека
    -1.57
    POSITIVE LOGITS
    -\
    1.60
    ]}$
    1.52
     „
    1.46
    atterns
    1.44
    ть
    1.41
    してました
    1.41
    словно
    1.38
    ...
    1.37
    しましたが
    1.35
    /
    1.34
    Activations Density 0.009%

    No Known Activations