© 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. 116872
    Prev
    Next
    INDEX
    Explanations

    stepping through code execution states

    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
    uzzy
    -0.69
     quorum
    -0.68
    eringer
    -0.66
    rafo
    -0.66
    planets
    -0.66
    instrument
    -0.66
    帛
    -0.66
    锢
    -0.66
    점
    -0.66
     klima
    -0.65
    POSITIVE LOGITS
     frames
    1.04
    frames
    1.01
    Frames
    0.88
     step
    0.88
     evaluated
    0.85
     stack
    0.84
     frame
    0.82
     eval
    0.82
    frame
    0.81
    评估
    0.81
    Activations Density 0.023%

    No Known Activations