© 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. 10591
    Prev
    Next
    INDEX
    Explanations

    TV series characters and places

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

    The main thing this neuron does is detect mentions of wolves or werewolf-related/supernatural content.

    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
     ſel
    -1.41
    nial
    -1.38
    yorsunuz
    -1.30
    撄
    -1.30
     errMsg
    -1.30
     totalCount
    -1.30
     hogares
    -1.27
    ceas
    -1.27
    pecabe
    -1.26
    ︐
    -1.23
    POSITIVE LOGITS
     \
    1.21
     they
    1.20
    rogène
    1.16
    以前
    1.09
    ksjoner
    1.09
     /\
    1.09
     =\
    1.07
     chứ
    1.05
    }=
    1.05
    =\
    1.05
    Activations Density 0.006%

    No Known Activations