© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10437
    Prev
    Next
    INDEX
    Explanations

    file paths

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

    relative file path references (e.g., "../../") in code or HTML documents.

    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
    e
    -2.38
    o
    -2.25
    ⇹
    -2.19
    
    -2.05
    猡
    -2.02
    鯔
    -2.00
    ```
    -1.98
     _________
    -1.97
    istocene
    -1.89
    快要
    -1.87
    POSITIVE LOGITS
    Despite
    2.67
    Using
    2.63
    After
    2.58
    Although
    2.52
    While
    2.48
    With
    2.45
     of
    2.44
    Through
    2.42
    Before
    2.33
    ↵
    2.31
    Activations Density 0.002%

    No Known Activations