© 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. 112885
    Prev
    Next
    INDEX
    Explanations

    video encoding or streaming

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

    technical video/image encoding formats and compression standards (like H.264, MPEG-4, YUV420).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     esigen
    -1.44
    หรือ
    -1.39
    倆
    -1.35
    一個人
    -1.27
     did
    -1.25
    俨
    -1.24
    也沒
    -1.23
     estekak
    -1.23
     sonno
    -1.23
     glowing
    -1.22
    POSITIVE LOGITS
    cción
    1.39
    材质
    1.38
     decoradas
    1.27
    ної
    1.26
    konfirmasi
    1.23
    螓
    1.23
    <0xB5>
    1.23
     suceder
    1.23
     MONTH
    1.22
     pracowników
    1.22
    Activations Density 0.019%

    No Known Activations