© 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. 10-GEMMASCOPE-RES-131K
    7. 884
    Prev
    Next
    INDEX
    Explanations

    and followed by another word

    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
    힛
    -1.59
    쨩
    -1.53
    
    -1.53
    いろいろな
    -1.47
     empfangen
    -1.46
    Obec
    -1.43
    閖
    -1.41
    废话
    -1.41
    Nép
    -1.40
    その他の
    -1.39
    POSITIVE LOGITS
     and
    2.06
    ↵↵↵
    1.77
    ’
    1.63
    楯
    1.60
     из
    1.55
     impulsar
    1.41
     which
    1.41
    ку
    1.40
    у
    1.37
    ge
    1.36
    Activations Density 0.060%

    No Known Activations