© 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. 102805
    Prev
    Next
    INDEX
    Explanations

    code identifiers and symbols

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

    uppercase identifiers or constants in code, particularly in configuration settings, annotations, and class/variable names.

    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
     Both
    -1.84
     with
    -1.82
     levantó
    -1.64
    '
    -1.64
    幼稚
    -1.58
     corriendo
    -1.55
    da
    -1.52
    不但
    -1.49
     registró
    -1.48
     pursuant
    -1.48
    POSITIVE LOGITS
    她的
    1.82
     её
    1.76
     нашу
    1.70
     одежды
    1.62
    ":"+
    1.60
     queridos
    1.55
    しましたが
    1.54
    ᅫ
    1.53
     ouvrage
    1.51
     GenerationType
    1.51
    Activations Density 0.001%

    No Known Activations