© 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. 70799
    Prev
    Next
    INDEX
    Explanations

    lower and upper bounds

    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
    핌
    -1.51
     问
    -1.48
     _________
    -1.47
    joyed
    -1.45
    according
    -1.41
     BERNAMA
    -1.38
    룽
    -1.36
     protože
    -1.34
    为啥
    -1.34
    olingo
    -1.32
    POSITIVE LOGITS
    Недостатки
    1.45
     just
    1.27
     not
    1.24
     apprehension
    1.23
     Ayrıca
    1.23
    ཋ
    1.22
     still
    1.22
     */
    1.20
    Плюсы
    1.20
    簟
    1.19
    Activations Density 0.004%

    No Known Activations