© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92004
    Prev
    Next
    INDEX
    Explanations

    snow traction spikes studded gear

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

    The neuron is keyed to spotting alphanumeric product or model identifiers—particularly tokens composed of uppercase letters and numbers.

    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
    肝
    -0.74
     Unmarshal
    -0.67
    ственном
    -0.67
     Colli
    -0.66
     ricar
    -0.66
     ("\
    -0.65
     Elbow
    -0.65
     Nozzle
    -0.64
     Cori
    -0.64
    validators
    -0.64
    POSITIVE LOGITS
     snow
    1.57
    snow
    1.36
     traction
    1.21
     spikes
    1.17
     Snow
    1.14
     snowy
    1.10
     cramp
    1.06
     studded
    1.05
     snowfall
    1.05
    Snow
    1.02
    Activations Density 0.022%

    No Known Activations