© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15735
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms

    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
    I
    -0.87
    <
    -0.85
    銲
    -0.82
    これから
    -0.79
    越来越多
    -0.79
    ोड़
    -0.79
     advancements
    -0.79
    tir
    -0.77
    ⤒
    -0.77
     cykel
    -0.75
    POSITIVE LOGITS
    ímite
    0.98
     estekak
    0.94
    Затем
    0.91
    できません
    0.91
     estas
    0.91
    نتیجه
    0.88
    怯
    0.87
    امکان
    0.87
     Bezirk
    0.85
    طرز
    0.85
    Activations Density 0.180%

    No Known Activations