© 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. 36504
    Prev
    Next
    INDEX
    Explanations

    total count items

    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
     now
    -1.15
     Familie
    -1.01
     incluye
    -1.01
     ন
    -1.01
    addRow
    -0.99
     company
    -0.98
     principali
    -0.96
    ₇
    -0.94
     including
    -0.94
    OrEqual
    -0.94
    POSITIVE LOGITS
    Эзо
    1.09
    Продол
    1.03
    余談
    1.00
    ִּ
    0.94
    orphic
    0.94
    //:
    0.93
    würdig
    0.93
    結局
    0.91
    Tekst
    0.90
    getNumberOf
    0.90
    Activations Density 0.005%

    No Known Activations