© 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. 67846
    Prev
    Next
    INDEX
    Explanations

    strength of

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

    The neuron activates on mentions of “strength” (i.e., it detects the word “strength” and its variants in technical contexts).

    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
    盌
    -2.94
    栳
    -2.69
     was
    -2.39
    u
    -2.36
    with
    -2.34
    er
    -2.33
     faſt
    -2.33
     teamed
    -2.25
    慙
    -2.14
    产品的
    -2.06
    POSITIVE LOGITS
     of
    3.50
    趼
    3.00
    渽
    2.67
    蛱
    2.58
    沕
    2.56
    ⩥
    2.50
     zwölf
    2.47
    .
    2.44
     gewisser
    2.42
    ⚣
    2.41
    Activations Density 0.008%

    No Known Activations