© 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. 48847
    Prev
    Next
    INDEX
    Explanations

    header, payload

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

    The neuron specializes in spotting standalone numeric literals (numbers) in code or technical text.

    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
    åg
    -0.75
    dani
    -0.74
     counterpart
    -0.71
     свя
    -0.71
    wyżs
    -0.71
    latz
    -0.71
     JSTOR
    -0.70
    opat
    -0.69
    Throughput
    -0.69
    ဋ
    -0.69
    POSITIVE LOGITS
     payload
    1.60
     header
    1.56
    header
    1.45
     headers
    1.40
     Payload
    1.36
    Payload
    1.35
    payload
    1.30
    headers
    1.27
    Header
    1.23
    hdr
    1.16
    Activations Density 0.032%

    No Known Activations