© 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. 65496
    Prev
    Next
    INDEX
    Explanations

    common phrases and code beginnings

    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
    h
    -2.75
    am
    -2.69
    .“
    -2.63
    ay
    -2.55
     membersihkan
    -2.53
    m
    -2.44
    are
    -2.39
    j
    -2.36
     è
    -2.33
     And
    -2.30
    POSITIVE LOGITS
    缯
    2.58
    쫀
    2.58
    휀
    2.47
    朏
    2.36
     sportowe
    2.36
     více
    2.36
    𝄆
    2.36
    讠
    2.34
    唞
    2.33
     قابلیت
    2.31
    Activations Density 0.000%

    No Known Activations