© 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. 48331
    Prev
    Next
    INDEX
    Explanations

    absolute basis / value / magnitude

    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
    nextProps
    -0.84
    Urls
    -0.82
    kii
    -0.78
     ขาว
    -0.75
    rollable
    -0.74
    isDebugEnabled
    -0.73
    moveToNext
    -0.72
    ㅜ
    -0.72
    RatingBar
    -0.72
    mergeFrom
    -0.71
    POSITIVE LOGITS
     absolute
    6.28
    absolute
    5.53
     Absolute
    4.84
    Absolute
    4.78
     абсолю
    4.44
    绝对
    4.06
    ABSOL
    3.63
     ABSOL
    3.59
     absol
    3.42
    絶対
    3.36
    Activations Density 0.108%

    No Known Activations