© 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. 113835
    Prev
    Next
    INDEX
    Explanations

    inline assembly and gas directives

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

    assembly language code and low-level programming constructs.

    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
     we
    -1.95
     devido
    -1.77
     compels
    -1.58
    ︲
    -1.54
     restricts
    -1.54
    ꦢ
    -1.49
    鉬
    -1.48
     discusses
    -1.45
     debido
    -1.44
     can
    -1.43
    POSITIVE LOGITS
     by
    1.51
     at
    1.35
     not
    1.34
    although
    1.28
    Ź
    1.23
    bringung
    1.21
    ysteme
    1.15
    鲸
    1.14
    Canal
    1.14
    They
    1.14
    Activations Density 0.043%

    No Known Activations