© 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. 34-GEMMASCOPE-RES-131K
    7. 64964
    Prev
    Next
    INDEX
    Explanations

    rapid prototyping and protocols

    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
     recib
    -0.89
     Maternal
    -0.88
     procura
    -0.85
     senza
    -0.85
    慢慢的
    -0.84
    mbgg
    -0.84
    sbs
    -0.82
    '
    -0.82
     NEW
    -0.82
     latter
    -0.82
    POSITIVE LOGITS
     prototyping
    1.47
    Rapid
    1.41
     Rapid
    1.39
     rapid
    1.20
    rapid
    1.10
    response
    1.09
     rapidly
    1.09
     Proto
    1.07
     onset
    1.07
    proto
    1.03
    Activations Density 0.025%

    No Known Activations