© 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. 101657
    Prev
    Next
    INDEX
    Explanations

    \[ ... \] syntax

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

    special characters and symbols that appear in technical or structured text formats like code, markup, or formatted data.

    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
     that
    -1.63
     this
    -1.40
     which
    -1.34
    ↵
    -1.33
     he
    -1.26
    諳
    -1.14
     also
    -1.14
     самого
    -1.13
     también
    -1.12
    薗
    -1.12
    POSITIVE LOGITS
    かかる
    1.37
    ᾗ
    1.24
     queridos
    1.24
    peur
    1.23
     venit
    1.17
    tidase
    1.17
     spus
    1.15
    gallon
    1.13
     vuestro
    1.13
     /**
    1.13
    Activations Density 0.002%

    No Known Activations