© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116323
    Prev
    Next
    INDEX
    Explanations

    version numbers, specs, and measurements

    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
    <>("
    -1.23
     especially
    -1.22
     ομά
    -1.19
     or
    -1.17
    ménage
    -1.15
    voegd
    -1.13
    mybatisplus
    -1.12
    терапия
    -1.11
     of
    -1.09
     beispielsweise
    -1.09
    POSITIVE LOGITS
     with
    2.02
     никаких
    1.32
     utilisant
    1.22
    Gön
    1.16
     using
    1.15
    ไม่มี
    1.08
     currently
    1.08
     no
    1.06
     utilisent
    1.05
     roughly
    1.01
    Activations Density 0.246%

    No Known Activations