© 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. 36142
    Prev
    Next
    INDEX
    Explanations

    section titles or labels

    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
    嘤
    -2.17
     mendengar
    -2.08
    इटम
    -2.06
     sempurna
    -2.03
    ﷽
    -1.99
     akrab
    -1.98
     lancar
    -1.95
    ｶ
    -1.95
     bahagia
    -1.95
     شیپور
    -1.95
    POSITIVE LOGITS
    ↵
    3.17
    '
    3.06
    9
    2.72
    -
    2.55
     decidedly
    2.55
    <em>
    2.53
    _
    2.52
    8
    2.50
    >
    2.48
    *
    2.47
    Activations Density 0.000%

    No Known Activations