© 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. 34-GEMMASCOPE-RES-131K
    7. 2535
    Prev
    Next
    INDEX
    Explanations

    supernatural species and beings

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

    The neuron activates on mentions of supernatural or fantasy beings (e.g. “Teen Wolf,” “demigods,” “monsters,” “werewolf”), effectively spotting references to non-human or magical creatures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    馃
    -0.85
     comercial
    -0.82
     invaders
    -0.79
    wikipedia
    -0.78
     hypocrite
    -0.77
     phal
    -0.77
    😗
    -0.77
    XOR
    -0.77
     sapat
    -0.76
    GOR
    -0.76
    POSITIVE LOGITS
     species
    1.43
     mutant
    1.38
     hybrid
    1.36
     humans
    1.31
     hybrids
    1.30
     human
    1.21
     Hybrid
    1.16
     supernatural
    1.13
     shifter
    1.11
     beings
    1.09
    Activations Density 0.044%

    No Known Activations