© 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. 22-GEMMASCOPE-RES-131K
    7. 34144
    Prev
    Next
    INDEX
    Explanations

    Muslim Marriage dating singles

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

    The neuron steadily ramps up activation as you move through the text, essentially marking how far into the document a token occurs.

    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
     haji
    -1.38
    🤬
    -1.25
     decidedly
    -1.23
     Pust
    -1.20
     entusias
    -1.18
     thwarted
    -1.16
     نقط
    -1.15
    ⅝
    -1.15
     kaos
    -1.14
     unending
    -1.13
    POSITIVE LOGITS
     Jego
    1.37
    ῾
    1.35
    hidupan
    1.24
     from
    1.23
     sehr
    1.21
     prominent
    1.20
     ње
    1.20
     very
    1.20
    ěte
    1.17
    hline
    1.16
    Activations Density 0.027%

    No Known Activations