© 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. 34-GEMMASCOPE-RES-131K
    4. 60484
    Prev
    Next
    INDEX
    Explanations

    absolute value or modulus

    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
    pered
    -0.68
    ënten
    -0.67
    累了
    -0.65
     Chiropractic
    -0.64
     Chancellor
    -0.64
    lblNewLabel
    -0.64
    Ĝ
    -0.64
    瓚
    -0.63
    боро
    -0.63
    倡
    -0.63
    POSITIVE LOGITS
    abs
    4.31
     abs
    4.22
     absolute
    3.81
    Abs
    3.77
    ABS
    3.52
     ABS
    3.36
     Abs
    3.34
    absolute
    3.22
     Absolute
    3.13
    Absolute
    3.03
    Activations Density 0.256%

    No Known Activations