© 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. 34-GEMMASCOPE-RES-131K
    7. 116734
    Prev
    Next
    INDEX
    Explanations

    linking to purpose

    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_34/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
     which
    -0.98
     this
    -0.94
     surprisingly
    -0.91
     so
    -0.90
     =>
    -0.90
     these
    -0.88
     where
    -0.85
     ensuring
    -0.84
     since
    -0.83
     because
    -0.82
    POSITIVE LOGITS
     intended
    1.68
     provided
    1.48
     meant
    1.46
    provided
    1.41
     offered
    1.38
    intended
    1.16
     supplied
    1.16
    Provided
    1.11
     protected
    1.09
     fourni
    1.09
    Activations Density 0.104%

    No Known Activations