© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103147
    Prev
    Next
    INDEX
    Explanations

    programming languages and technologies

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

    technical terms and identifiers in programming contexts, particularly related to code syntax, file paths, and programming language keywords.

    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
    ari
    -1.38
     ơi
    -1.28
     –
    -1.26
     from
    -1.26
    İL
    -1.20
     télécommande
    -1.20
     into
    -1.19
     on
    -1.17
     extraordinaire
    -1.15
     文章
    -1.15
    POSITIVE LOGITS
    這些
    1.62
     Otras
    1.51
     Эти
    1.48
     when
    1.47
     or
    1.45
     ocurrió
    1.44
     auténtica
    1.43
     Empieza
    1.42
    這種
    1.41
    inguez
    1.39
    Activations Density 0.274%

    No Known Activations