© 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. 102859
    Prev
    Next
    INDEX
    Explanations

    SDK and related frameworks

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

    the acronym "SDK" (Software Development Kit) in programming and technical contexts.

    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
     Because
    -2.34
     stuffy
    -2.30
     murky
    -2.28
     What
    -2.16
    arraycopy
    -2.14
     статті
    -2.08
     Що
    -2.08
    because
    -2.05
    </h3>
    -2.03
     If
    -2.03
    POSITIVE LOGITS
    та
    2.47
    i
    2.39
    ࿚
    2.31
     we
    2.28
    \}$,
    2.08
    Your
    2.05
     receber
    2.03
    鬟
    2.02
     desenli
    2.02
    ”,
    2.02
    Activations Density 0.005%

    No Known Activations