© 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. 78517
    Prev
    Next
    INDEX
    Explanations

    square, rectangular

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is primarily picking up on numeric‐and‐punctuation tokens and surrounding words in technical enumerations or formula‐style descriptions (e.g. numbers, commas, parentheses, “forming,” “rectangle,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Spherical
    -1.23
     spherical
    -1.20
     conical
    -1.15
    spher
    -1.14
     curved
    -1.10
     cones
    -1.02
     diameter
    -1.01
    Cone
    -1.01
     cone
    -1.00
     Diameter
    -1.00
    POSITIVE LOGITS
     square
    3.73
    square
    3.16
     squares
    2.94
     Square
    2.94
    Square
    2.86
     SQUARE
    2.67
     rectangular
    2.64
    SQUARE
    2.55
     rectangle
    2.48
    squares
    2.38
    Activations Density 0.094%

    No Known Activations