© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84407
    Prev
    Next
    INDEX
    Explanations

    BOOST_CHECK, is a, self;

    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_34/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
     Paramètres
    -1.14
    を探す
    -1.09
     Seleccione
    -1.09
     Améli
    -1.03
    清爽
    -1.03
    actéristi
    -1.02
     razu
    -1.02
     Préférences
    -1.02
    albeit
    -1.00
    把他
    -1.00
    POSITIVE LOGITS
     seemingly
    1.12
    IQUES
    0.96
     înainte
    0.94
    ÍC
    0.94
     skydd
    0.92
    ♗
    0.92
     completely
    0.91
     partly
    0.90
    備考
    0.89
    ÁN
    0.88
    Activations Density 0.012%

    No Known Activations