© 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. 22-GEMMASCOPE-RES-131K
    7. 84489
    Prev
    Next
    INDEX
    Explanations

    political commentary and views

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

    The neuron specializes in detecting numerical tokens—years, dates, and other number sequences.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     technically
    -1.20
    𝓉
    -1.13
    onclick
    -1.10
     техні
    -1.09
    merkung
    -1.07
     picante
    -1.05
     alcoh
    -1.05
    +#
    -1.03
     each
    -1.02
    хин
    -1.02
    POSITIVE LOGITS
     anti
    1.59
     views
    1.28
     jengibre
    1.23
     political
    1.23
     анти
    1.20
     srdce
    1.14
     problémy
    1.14
    larımız
    1.11
     hermosas
    1.09
     costado
    1.07
    Activations Density 0.151%

    No Known Activations