© 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. 10-GEMMASCOPE-RES-131K
    7. 113450
    Prev
    Next
    INDEX
    Explanations

    academic papers and essays

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

    This neuron detects mentions of formal written works or academic document types (e.g. essay, paper, thesis, case study).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    urants
    -1.64
    antaranya
    -1.55
    springen
    -1.50
     todella
    -1.49
     potret
    -1.47
    Sinopse
    -1.46
    Distribución
    -1.44
     étoit
    -1.39
     zowel
    -1.38
     kommende
    -1.38
    POSITIVE LOGITS
     their
    1.65
    ar
    1.63
    }
    1.62
     as
    1.48
    se
    1.46
     told
    1.41
     make
    1.41
    !
    1.40
     decide
    1.38
    ed
    1.37
    Activations Density 0.002%

    No Known Activations