© 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. 84453
    Prev
    Next
    INDEX
    Explanations

    risk factors and communication

    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
    The
    -2.33
    After
    -2.06
    Honestly
    -1.66
    Ultimately
    -1.64
    When
    -1.59
    ?”
    -1.57
    ″
    -1.54
     });
    -1.52
    ())))
    -1.52
     你
    -1.51
    POSITIVE LOGITS
     andere
    1.73
     связанные
    1.65
    働く
    1.63
    找个
    1.62
     lurking
    1.54
     cantantes
    1.52
     compartido
    1.47
    꽤
    1.45
     ако
    1.45
     mindig
    1.45
    Activations Density 0.036%

    No Known Activations