© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25200
    Prev
    Next
    INDEX
    Explanations

    mini [descriptor]

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

    The neuron detects occurrences of the substring “mini” (i.e. words or compounds beginning with “mini”).

    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
     แต่
    -2.69
    ↵↵
    -2.64
    le
    -2.45
     worin
    -2.44
    
    -2.39
    ll
    -2.38
    >
    -2.38
    sandalia
    -2.34
    夬
    -2.33
    訫
    -2.33
    POSITIVE LOGITS
    During
    3.84
    Through
    3.66
    Before
    3.52
    While
    3.50
    After
    3.45
    Following
    3.44
    Some
    3.38
    Using
    3.36
    When
    3.23
    Almost
    3.19
    Activations Density 0.025%

    No Known Activations