© 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. 58937
    Prev
    Next
    INDEX
    Explanations

    upgrading and upgraded software

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

    The neuron responds to occurrences of the root “upgrad” (e.g. upgrade, upgrading, upgraded) in text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ).
    -2.22
    </h2>
    -1.68
    -
    -1.59
    }")
    -1.55
    /
    -1.53
    1
    -1.52
    B
    -1.49
    }");
    -1.48
    n
    -1.45
    ांकि
    -1.45
    POSITIVE LOGITS
    嫪
    2.28
    橚
    2.09
    得上
    1.84
    訕
    1.77
    怍
    1.77
     ſte
    1.77
    媜
    1.76
     มี
    1.73
     aspetti
    1.71
    妡
    1.71
    Activations Density 0.031%

    No Known Activations