© 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. 31082
    Prev
    Next
    INDEX
    Explanations

    supernatural ghost scares

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

    The neuron “lights up” on content‐bearing words (especially nouns and adjectives) rather than on function words or punctuation.

    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
    Prison
    -0.91
    Anmeldung
    -0.86
     alts
    -0.83
    unused
    -0.82
    zeln
    -0.81
    𝗼
    -0.80
     رتبه
    -0.79
    ଉ
    -0.79
    atother
    -0.78
    OBJETIVOS
    -0.78
    POSITIVE LOGITS
     supernatural
    1.10
     paranormal
    0.98
     exor
    0.98
    Coff
    0.93
     Ghost
    0.91
     ghost
    0.90
     Uncle
    0.86
     scares
    0.84
     Professor
    0.78
     village
    0.77
    Activations Density 0.001%

    No Known Activations