© 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. 10-GEMMASCOPE-RES-131K
    7. 39774
    Prev
    Next
    INDEX
    Explanations

    stream related contexts

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

    The neuron fires whenever the text mentions a “stream” (e.g. data stream, media stream, stream cipher).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    4
    -3.14
    2
    -2.91
    7
    -2.81
    6
    -2.78
    3
    -2.72
    8
    -2.64
    5
    -2.44
    and
    -2.41
    9
    -2.41
    ↵↵
    -2.28
    POSITIVE LOGITS
    zdroj
    2.09
    archiwizowane
    1.92
    ꯴
    1.91
    ଴
    1.88
    ୪
    1.86
    ︓
    1.83
     kasus
    1.80
    цію
    1.78
    sprzedam
    1.78
    旆
    1.77
    Activations Density 0.064%

    No Known Activations