© 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. 10-GEMMASCOPE-RES-131K
    7. 10325
    Prev
    Next
    INDEX
    Explanations

    names, programming, intramuscular

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

    non-English words or phrases, particularly from Spanish and programming contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    words related to "obtaining" or "getting" something, particularly in technical/programming contexts (like FirstOrDefault methods) or Spanish "obtener" (to obtain).

    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
    {
    -3.13
     The
    -3.03
    '
    -2.59
     they
    -2.48
    "
    -2.42
     '
    -2.39
    pecabe
    -2.39
    럿
    -2.33
    }$
    -2.28
     regiões
    -2.27
    POSITIVE LOGITS
    諴
    3.50
    趼
    3.42
    鈊
    2.94
    𓆜
    2.92
    疳
    2.81
    읊
    2.72
    इटम
    2.72
    骓
    2.69
    摃
    2.67
    ه
    2.66
    Activations Density 0.005%

    No Known Activations