© 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. 93612
    Prev
    Next
    INDEX
    Explanations

    commands or technical questions

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

    The neuron strongly activates on command‐line streaming protocol fragments—especially RTSP URLs (e.g. “rtsp://…”) and related VLC/network‐caching flags.

    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
    dAtA
    -0.88
     کسی
    -0.79
    قه
    -0.79
    newInstance
    -0.77
    rieux
    -0.76
    initData
    -0.73
     storylines
    -0.73
     recesses
    -0.72
     ガー
    -0.72
    romo
    -0.71
    POSITIVE LOGITS
     VLC
    0.84
     VL
    0.77
    部は
    0.75
    ächtig
    0.72
     oameni
    0.72
    holic
    0.71
    pista
    0.71
     koch
    0.71
    skinned
    0.70
     Ory
    0.70
    Activations Density 0.073%

    No Known Activations