© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85393
    Prev
    Next
    INDEX
    Explanations

    East German regimes and eras

    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
     this
    -1.55
     for
    -1.55
    AÇÃO
    -1.30
    🤬
    -1.27
    😂😂😂
    -1.27
     triliun
    -1.27
    blurRadius
    -1.27
    ancio
    -1.23
    <bos>
    -1.20
    </tr>
    -1.20
    POSITIVE LOGITS
    ğiniz
    1.59
    欒
    1.50
     niem
    1.33
     adaptarse
    1.31
     całego
    1.31
    сколько
    1.27
     produkcji
    1.27
     ANOTHER
    1.25
     financiera
    1.23
    
    1.23
    Activations Density 0.040%

    No Known Activations