© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41512
    Prev
    Next
    INDEX
    Explanations

    words starting with Min

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

    The neuron fires strongly on tokens that begin with the string “Min” (e.g. “MinD,” “Minu…,” “Minhag,” “Minikube,” etc.).

    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
    鬟
    -2.70
     vuelven
    -2.67
    
    -2.64
    $",
    -2.56
     Acuerdo
    -2.52
    \",\
    -2.50
     beliebtesten
    -2.50
    ,))
    -2.48
    ”,
    -2.48
    ]');
    -2.42
    POSITIVE LOGITS
    1
    4.19
    9
    2.97
     =
    2.92
    2
    2.91
    0
    2.75
    at
    2.58
    -
    2.58
    providedIn
    2.56
    _
    2.55
    3
    2.55
    Activations Density 0.007%

    No Known Activations