© 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. 62786
    Prev
    Next
    INDEX
    Explanations

    point written mechanical P.D.I check

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

    The neuron strongly activates on numeric tokens and measurements (e.g. digits, version numbers, point counts).

    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
    RST
    -0.82
    Segment
    -0.80
     Howell
    -0.70
     NVIDIA
    -0.69
    rusted
    -0.69
    Visit
    -0.68
     против
    -0.67
    clos
    -0.67
    dumps
    -0.66
    Implicit
    -0.66
    POSITIVE LOGITS
    Rai
    0.68
    捆
    0.67
    umptions
    0.64
    userManager
    0.64
    Sma
    0.63
    iddharth
    0.63
     todd
    0.62
    引起了
    0.61
     Rainer
    0.60
     auster
    0.60
    Activations Density 0.052%

    No Known Activations