© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42988
    Prev
    Next
    INDEX
    Explanations

    Nicki Minaj, Ivorian, Islander peoples

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

    The neuron responds strongly to occurrences of the word “miners” (i.e. references to mining workers).

    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
     Hinblick
    -2.86
     weißem
    -2.36
    千萬
    -2.27
     일본
    -2.25
     그는
    -2.23
     verstär
    -2.22
     mocno
    -2.22
     selben
    -2.19
     elektrick
    -2.17
    髕
    -2.17
    POSITIVE LOGITS
    s
    2.30
    </b>
    2.19
     *****
    2.17
     ????
    2.14
     lus
    2.11
    </h1>
    2.08
     的
    2.05
    itiert
    2.00
     если
    1.98
     在
    1.95
    Activations Density 0.003%

    No Known Activations