© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113622
    Prev
    Next
    INDEX
    Explanations

    http or location endings

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

    fragments of camelCase identifiers in code, particularly partial words within compound programming terms.

    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
     if
    -1.54
    If
    -1.42
    ться
    -1.38
    )
    -1.34
    We
    -1.31
    }(
    -1.30
     melap
    -1.27
    lapis
    -1.24
     eficacia
    -1.24
    Our
    -1.24
    POSITIVE LOGITS
    d
    1.61
     également
    1.37
    henge
    1.30
    顺着
    1.26
    cists
    1.25
     meager
    1.22
     tém
    1.19
     чёр
    1.18
    ค่ะ
    1.18
    Maui
    1.17
    Activations Density 0.166%

    No Known Activations