© 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. 10-GEMMASCOPE-RES-131K
    7. 98787
    Prev
    Next
    INDEX
    Explanations

    hopes and expectations

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

    The neuron fires on hyperbolic or superlative expressions—idioms and intensifiers that convey exaggeration or “too-much” extremes (e.g. “too good to be true,” “shoot for the stars,” “wildest expectations”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     in
    -1.45
     sterke
    -1.32
    libatkan
    -1.32
     runde
    -1.31
     giocatore
    -1.30
    woordig
    -1.26
    wiſe
    -1.22
     the
    -1.21
     spannend
    -1.20
    記得
    -1.19
    POSITIVE LOGITS
    都能
    1.53
    en
    1.48
    p
    1.42
    ti
    1.41
    up
    1.38
    us
    1.38
     hoped
    1.38
    b
    1.38
    ke
    1.37
    an
    1.36
    Activations Density 0.038%

    No Known Activations