© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59098
    Prev
    Next
    INDEX
    Explanations

    memorable and unforgettable

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

    This neuron detects adjectives emphasizing how memorable or unforgettable something is.

    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
     memutus
    -2.45
     melindungi
    -2.14
     mengatasi
    -2.09
     memudahkan
    -2.08
     häufigsten
    -1.99
     mewujudkan
    -1.96
     kontinuier
    -1.93
     wesentlich
    -1.88
     memperbaiki
    -1.88
    ጐ
    -1.88
    POSITIVE LOGITS
    '
    2.13
    We
    2.11
    (
    1.96
    He
    1.82
     and
    1.80
     To
    1.79
     –
    1.75
    d
    1.73
    鸶
    1.72
    R
    1.68
    Activations Density 0.004%

    No Known Activations