© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59603
    Prev
    Next
    INDEX
    Explanations

    abbreviations and code segments

    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
    を
    -1.23
    があり
    -1.22
    Preparazione
    -1.12
    問題は
    -1.09
    あるいは
    -1.09
    時間は
    -1.09
    があります
    -1.03
    と
    -1.02
     is
    -1.02
    ～～
    -1.02
    POSITIVE LOGITS
    Ꮴ
    1.45
    ཥ
    1.44
    をしていた
    1.31
    masyarakat
    1.31
     lác
    1.28
     applau
    1.27
     пальто
    1.26
     ВО
    1.23
    の為
    1.22
     mélanger
    1.21
    Activations Density 0.139%

    No Known Activations