© 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. 127698
    Prev
    Next
    INDEX
    Explanations

    time measured in decades

    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
     cuando
    -2.02
    ℣
    -1.98
     mejoras
    -1.90
     industrias
    -1.88
     successivamente
    -1.88
    
    -1.88
    明確
    -1.87
    🌛
    -1.85
     verbess
    -1.84
    ⟐
    -1.84
    POSITIVE LOGITS
    ’
    3.08
    </em>
    2.89
    0
    2.84
    '
    2.58
    i
    2.41
    per
    2.33
    )
    2.28
    â
    2.27
    /*
    2.20
    \_
    2.19
    Activations Density 0.010%

    No Known Activations