© 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. 34-GEMMASCOPE-RES-131K
    7. 57349
    Prev
    Next
    INDEX
    Explanations

    code attribute

    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
    桧
    -1.30
    』『
    -1.25
    数年
    -1.16
    ⁉
    -1.16
    bedien
    -1.15
    ❗️
    -1.13
    rechten
    -1.13
    星空
    -1.13
    ｡
    -1.13
    便秘
    -1.11
    POSITIVE LOGITS
     attribute
    1.23
     item
    1.22
     специалисты
    1.20
    远处
    1.20
    なんだろう
    1.16
    麻煩
    1.14
     transaction
    1.13
    ή
    1.13
    过后
    1.13
    なのかな
    1.11
    Activations Density 0.173%

    No Known Activations