© 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. 44603
    Prev
    Next
    INDEX
    Explanations

    Fos fossil foolish

    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
    of
    -3.52
    there
    -3.39
    which
    -3.05
    on
    -2.72
    when
    -2.67
     There
    -2.64
     hain
    -2.52
    With
    -2.45
    Very
    -2.42
    Even
    -2.42
    POSITIVE LOGITS
    umpulan
    2.58
    鯷
    2.52
    怍
    2.47
    
    2.42
    𓁹
    2.42
    ];
    2.34
     queste
    2.33
    !”
    2.31
    ֟
    2.31
     gemessen
    2.30
    Activations Density 0.002%

    No Known Activations