© 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. 23925
    Prev
    Next
    INDEX
    Explanations

    karma test

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

    The neuron detects mentions of the term “karma” (in any casing).

    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
    </h3>
    -3.13
     französische
    -2.98
    CurtirCurtir
    -2.91
    遹
    -2.80
     Anſ
    -2.66
    哢
    -2.66
     considerare
    -2.64
    л
    -2.63
    Zubereitung
    -2.59
     utilizzare
    -2.52
    POSITIVE LOGITS
    e
    2.44
    .
    2.42
    欒
    2.39
    </b>
    2.27
    𝐒
    2.23
    餉
    2.22
    挲
    2.20
    ጴ
    2.14
    缉
    2.11
    <
    2.05
    Activations Density 0.002%

    No Known Activations