© 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. 113094
    Prev
    Next
    INDEX
    Explanations

    papers and legal documents

    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
     longstanding
    -1.91
     reinforces
    -1.86
    Usually
    -1.80
     heightened
    -1.80
     Generally
    -1.79
    Shortly
    -1.78
     furthering
    -1.78
     Without
    -1.78
     supremely
    -1.76
     Usually
    -1.75
    POSITIVE LOGITS
    a
    1.58
     –
    1.46
    '
    1.45
    ↵↵
    1.43
     you
    1.41
    𝅥
    1.40
     \
    1.39
     MILLION
    1.38
    aien
    1.34
    ‘
    1.34
    Activations Density 0.201%

    No Known Activations