© 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. 10-GEMMASCOPE-RES-131K
    7. 41999
    Prev
    Next
    INDEX
    Explanations

    fluctuations

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

    This neuron detects the term “fluctuations,” i.e. explicit mentions of variability or change.

    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
    逦
    -3.06
    裃
    -3.06
     collezione
    -2.97
     recensione
    -2.95
    蚺
    -2.91
    💢
    -2.88
    鏵
    -2.80
    Bakgrunns
    -2.77
    毟
    -2.66
     aboli
    -2.63
    POSITIVE LOGITS
    2
    3.84
    ]
    3.48
    i
    3.48
    g
    3.47
    .
    3.38
    3
    3.17
    w
    3.14
    ,"
    3.05
    }
    3.00
     $
    2.98
    Activations Density 0.009%

    No Known Activations