© 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. 63675
    Prev
    Next
    INDEX
    Explanations

    rods, tubes, plates, dises

    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
    　　「
    -0.80
     brushless
    -0.80
     trico
    -0.80
     professions
    -0.79
     チェーン
    -0.78
     kiln
    -0.78
     appell
    -0.76
     gameOver
    -0.76
     benzina
    -0.75
     gsm
    -0.75
    POSITIVE LOGITS
     plates
    1.50
     tubes
    1.28
     rods
    1.27
     discs
    1.27
     plate
    1.25
     pads
    1.23
     tiles
    1.23
     boxes
    1.22
     tube
    1.22
     tablets
    1.17
    Activations Density 0.556%

    No Known Activations