© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99167
    Prev
    Next
    INDEX
    Explanations

    Koch, Kochi, Kochanowski, getch

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    摃
    -3.13
    StoryboardSegue
    -3.09
    訁
    -2.98
     男孩
    -2.52
    灃
    -2.48
    瞜
    -2.48
    聼
    -2.47
     französ
    -2.47
    नलोड
    -2.45
    鈊
    -2.44
    POSITIVE LOGITS
            
    3.05
    -
    2.50
     dicono
    2.45
    家乡
    2.39
    0
    2.39
    and
    2.34
     и
    2.31
    ೣ
    2.30
    และ
    2.30
     \&
    2.25
    Activations Density 0.002%

    No Known Activations