© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74781
    Prev
    Next
    INDEX
    Explanations

    best [noun/category]

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

    The neuron activates strongly on superlative adjectives (especially “best” and similar “most …‐” constructions).

    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
    icksburg
    -1.55
    欲望
    -1.48
    鹵
    -1.48
     ongeveer
    -1.47
    散文
    -1.44
    前世
    -1.43
    幼稚
    -1.42
    millimeters
    -1.41
    ificant
    -1.38
    antism
    -1.38
    POSITIVE LOGITS
     auguri
    1.48
     acidente
    1.41
     such
    1.37
     lancar
    1.36
     cerdas
    1.32
     ferrovia
    1.32
     of
    1.32
    sr
    1.30
     ){
    1.27
     pisang
    1.27
    Activations Density 0.024%

    No Known Activations