© 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. 68152
    Prev
    Next
    INDEX
    Explanations

    masked or stringent

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

    The neuron fires on words containing the “mask” root (e.g. masked, masking, unmasked).

    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
    xvii
    -2.44
    t
    -2.31
    \
    -2.28
     洗面
    -2.14
     ‘’
    -2.09
    .
    -2.06
    ☆☆☆☆
    -2.06
    {
    -2.00
     nächste
    -1.92
    xiii
    -1.91
    POSITIVE LOGITS
    This
    2.72
    磲
    2.69
    }$
    2.45
     так
    2.42
    後記
    2.34
     reaffirmed
    2.23
    湖北
    2.19
    ～～
    2.19
    　　*
    2.19
    ～～～
    2.14
    Activations Density 0.024%

    No Known Activations