© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20598
    Prev
    Next
    INDEX
    Explanations

    personal statements or admissions

    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
    :
    -1.64
     وزارة
    -1.46
     saranno
    -1.45
    $
    -1.42
    怎么
    -1.41
     znajdziesz
    -1.41
    ;
    -1.41
    探索
    -1.38
     visas
    -1.36
    <em>
    -1.35
    POSITIVE LOGITS
     their
    1.63
     suministro
    1.56
     if
    1.46
    owment
    1.45
     that
    1.41
     they
    1.39
    They
    1.36
    Ꮏ
    1.36
     шоколад
    1.35
     denominado
    1.35
    Activations Density 0.025%

    No Known Activations