© 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. 57395
    Prev
    Next
    INDEX
    Explanations

    case numbers starting with C or CV

    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
     ۳۰
    -1.59
     these
    -1.52
    6
    -1.47
     chrétien
    -1.46
     however
    -1.41
     ۲۵
    -1.41
     .
    
    -1.40
     cuillère
    -1.36
     veau
    -1.31
    7
    -1.30
    POSITIVE LOGITS
     empuj
    1.45
    НАЯ
    1.37
     they
    1.34
    g
    1.25
     there
    1.23
    asil
    1.23
     prácticamente
    1.21
     от
    1.20
    ตัว
    1.20
    ることができます
    1.20
    Activations Density 0.766%

    No Known Activations