© 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. 22-GEMMASCOPE-RES-131K
    7. 130802
    Prev
    Next
    INDEX
    Explanations

    admin functions

    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_22/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
     Of
    -2.89
    '
    -2.55
    以免
    -2.42
     erklär
    -2.36
     Then
    -2.34
    轳
    -2.33
     Its
    -2.30
     takže
    -2.28
     womit
    -2.28
     It
    -2.27
    POSITIVE LOGITS
    狆
    3.23
    ୈ
    3.14
    喁
    3.02
    m
    2.59
    悒
    2.56
    Ꮂ
    2.53
    ed
    2.47
    🐱
    2.44
    ଃ
    2.39
    㐂
    2.36
    Activations Density 0.006%

    No Known Activations