© 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. 10200
    Prev
    Next
    INDEX
    Explanations

    unnoticed, underrated, underestimated, overlooked

    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_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
     estos
    -2.42
    Karakteristik
    -2.36
    翃
    -2.28
    UTIONS
    -2.27
     เพราะ
    -2.14
     aktiven
    -2.05
     dichas
    -1.99
     gezeigt
    -1.99
     hará
    -1.98
    婚礼
    -1.97
    POSITIVE LOGITS
    ↵
    3.09
    .
    2.30
     and
    2.13
    '
    2.13
     –
    2.00
    های
    1.84
     imposing
    1.83
    <em>
    1.82
    них
    1.80
     underrated
    1.79
    Activations Density 0.003%

    No Known Activations