© 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. 22-GEMMASCOPE-RES-131K
    7. 129857
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to sensational, attention‐grabbing headline language—i.e. hyperbolic or dramatic phrasing (like “This is HUGE,” “Breaking:,” emphatic dashes) typical of clickbait‐style reports.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    declaration or strong statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ׇ
    -1.34
     htmlFor
    -1.19
     består
    -1.13
    ֫
    -1.13
    ֺ
    -1.10
    gemaakt
    -1.09
     géographie
    -1.09
     ché
    -1.09
     alguns
    -1.07
     😊
    -1.07
    POSITIVE LOGITS
     this
    1.56
    ּוֹ
    1.51
     should
    1.36
     clearly
    1.24
    ְּ
    1.13
    cookieParser
    1.11
     Clearly
    1.10
    וּ
    1.10
     claramente
    1.09
    ֶּ
    1.09
    Activations Density 0.056%

    No Known Activations