© 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. 15628
    Prev
    Next
    INDEX
    Explanations

    legend / legends

    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
    ꜆
    -2.78
     включая
    -2.52
    
    -2.39
    ౮
    -2.34
    虓
    -2.23
    玧
    -2.19
     pacientes
    -2.16
    辚
    -2.09
    𖤍
    -2.09
    蕻
    -2.08
    POSITIVE LOGITS
    ؛
    2.53
    他在
    2.23
     bogotá
    2.16
     of
    2.14
    寕
    2.05
    尤其
    2.03
     retrô
    2.03
    </h2>
    2.03
    あっという間に
    2.03
     –
    2.02
    Activations Density 0.004%

    No Known Activations