© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14785
    Prev
    Next
    INDEX
    Explanations

    explaining how or why

    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
     during
    -1.48
    Morfo
    -1.36
     сообщил
    -1.28
     when
    -1.27
     hablaba
    -1.14
    During
    -1.13
    した場合
    -1.13
    Specifik
    -1.12
    ︓
    -1.11
     menyimpan
    -1.10
    POSITIVE LOGITS
     workable
    1.20
    FontOfSize
    1.19
     treten
    1.17
    riente
    1.17
     março
    1.16
    分析
    1.16
     ourselves
    1.16
     což
    1.14
    σουμε
    1.13
    遇
    1.13
    Activations Density 0.064%

    No Known Activations