© 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. 22-GEMMASCOPE-RES-131K
    4. 93252
    Prev
    Next
    INDEX
    Explanations

    possessives following nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     that
    -2.70
     around
    -2.03
     just
    -1.98
     before
    -1.83
     from
    -1.83
     what
    -1.82
     this
    -1.74
    Some
    -1.71
     during
    -1.71
     so
    -1.66
    POSITIVE LOGITS
    의
    2.09
    了几
    1.75
     Ministre
    1.73
    mathrm
    1.72
    ’
    1.67
     enorme
    1.66
     restant
    1.63
    鼍
    1.59
    <bos>
    1.58
    %%%%%%%%%%%%
    1.56
    Activations Density 0.036%

    No Known Activations