© 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. 33457
    Prev
    Next
    INDEX
    Explanations

    quantum spin Hall effect

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

    The neuron activates on uppercase‐heavy tokens—acronyms, abbreviations, and technical identifiers (e.g. all‐caps terms and code‐style names with capitals and digits).

    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
    6
    -1.84
    9
    -1.80
    5
    -1.80
    7
    -1.77
    3
    -1.66
    8
    -1.63
    1
    -1.59
    2
    -1.49
    The
    -1.48
     Nevertheless
    -1.41
    POSITIVE LOGITS
     سایر
    1.41
    medriver
    1.35
    
    1.16
    。<
    1.15
     vårt
    1.13
    quelize
    1.12
     gruesa
    1.11
     ])
    1.09
    CHREIBUNG
    1.09
     Bezeichnung
    1.08
    Activations Density 0.372%

    No Known Activations