© 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. 113119
    Prev
    Next
    INDEX
    Explanations

    changes to

    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
    )
    -1.69
    嗐
    -1.63
    बाइल
    -1.56
    "
    -1.55
    ſition
    -1.48
     relieves
    -1.48
    中途
    -1.47
     panneaux
    -1.41
    ients
    -1.41
    讫
    -1.40
    POSITIVE LOGITS
     the
    3.14
    那你
    1.84
    ↵
    1.82
     our
    1.80
    autogui
    1.66
     století
    1.65
     университета
    1.64
    谞
    1.60
     från
    1.59
    婀
    1.59
    Activations Density 0.026%

    No Known Activations