© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54211
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

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

    code and technical document formatting elements, particularly in JSON, markdown, and programming contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    子が
    -1.17
     investiga
    -1.13
    后再
    -1.02
     ją
    -1.00
     you
    -0.98
    ERMIN
    -0.97
    ὸ
    -0.96
    }));
    -0.96
     graciously
    -0.94
    ագրություններ
    -0.94
    POSITIVE LOGITS
    Lastname
    1.28
    hashMap
    1.11
    了起来
    1.09
     szczeg
    1.06
     мужская
    1.02
    了啊
    1.00
     bluz
    0.97
    츨
    0.96
    ímos
    0.95
    iiii
    0.95
    Activations Density 0.003%

    No Known Activations