© 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. 48802
    Prev
    Next
    INDEX
    Explanations

    hole, slot, groove, valve

    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
    annya
    -0.84
    หรือ
    -0.81
    alamualaikum
    -0.80
    FFEE
    -0.80
     compacto
    -0.79
    ciences
    -0.78
    authenticated
    -0.78
     wands
    -0.77
    baseUrl
    -0.77
     sə
    -0.77
    POSITIVE LOGITS
     holes
    2.41
     slots
    1.73
     hole
    1.73
     grooves
    1.63
     groove
    1.54
     Holes
    1.49
    Holes
    1.47
    holes
    1.45
     slot
    1.41
    slots
    1.36
    Activations Density 0.139%

    No Known Activations