© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101928
    Prev
    Next
    INDEX
    Explanations

    weak

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

    The neuron consistently activates on occurrences of the root “weak” (e.g. “weak,” “weakly,” etc.).

    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
     consentimento
    -3.09
    ’
    -3.05
    翃
    -3.00
     spearheaded
    -2.98
     semelh
    -2.97
     extremely
    -2.83
     predominantly
    -2.81
    轳
    -2.77
     orchestrated
    -2.77
     amazingly
    -2.75
    POSITIVE LOGITS
    0
    3.00
    或
    2.98
    s
    2.80
    8
    2.80
    晅
    2.75
     или
    2.64
    7
    2.59
     或
    2.58
    ish
    2.56
    ！”
    2.56
    Activations Density 0.005%

    No Known Activations