© 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. 34-GEMMASCOPE-RES-131K
    7. 92916
    Prev
    Next
    INDEX
    Explanations

    can do

    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
    Tabs
    -0.84
    Ϯ
    -0.83
    ukunfts
    -0.82
    ㄚ
    -0.74
    lería
    -0.73
     sudo
    -0.71
    StartsWith
    -0.71
     Brady
    -0.70
    jdk
    -0.69
    StringVar
    -0.69
    POSITIVE LOGITS
     carve
    2.72
     carving
    2.47
     carved
    2.23
     squeeze
    2.08
     squeezed
    1.88
     allocate
    1.85
     squeezing
    1.84
    carved
    1.73
     allocating
    1.73
     dedicate
    1.66
    Activations Density 0.059%

    No Known Activations