© 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. 34-GEMMASCOPE-RES-131K
    7. 38137
    Prev
    Next
    INDEX
    Explanations

    analyze studies and data

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

    The neuron fires on text that lays out concrete item specifications or feature lists—descriptions of what something is made of, how it’s constructed, or what it contains.

    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
    Anybody
    -1.76
    Though
    -1.52
     anybody
    -1.48
    Everybody
    -1.44
    everybody
    -1.43
     geologic
    -1.41
     Anybody
    -1.41
     foes
    -1.38
     yearly
    -1.36
     ought
    -1.33
    POSITIVE LOGITS
     XNUMX
    1.48
     ​​
    1.41
     analyzes
    1.29
     !!
    1.19
     ie
    1.16
    ̵
    1.13
     .:
    1.11
     և
    1.10
     .;
    1.06
     approx
    1.05
    Activations Density 0.028%

    No Known Activations