© 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. 12624
    Prev
    Next
    INDEX
    Explanations

    Acosta, chromium, Kuro, vermectin

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

    proper names or technical terms that appear in programming, math, or religious 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_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
    沄
    -3.23
    ⢓
    -3.22
    sandalia
    -3.00
    沇
    -2.89
    淠
    -2.89
    グルト
    -2.86
    𞤢
    -2.83
    骜
    -2.80
    鿬
    -2.77
    鉝
    -2.77
    POSITIVE LOGITS
    s
    3.45
     vorigen
    3.14
     
    3.08
     Einzelnen
    2.98
    re
    2.88
     }
    2.83
    c
    2.78
     Gegensatz
    2.69
    ts
    2.66
     Reliable
    2.53
    Activations Density 0.022%

    No Known Activations