© 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. 65345
    Prev
    Next
    INDEX
    Explanations

    ensure, VM, professional, elegant

    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
     clô
    -1.34
     libéral
    -1.20
     ДЛЯ
    -1.20
    ̨
    -1.16
     écou
    -1.14
    adalah
    -1.13
     prét
    -1.12
    jednoc
    -1.10
     réve
    -1.08
     relâche
    -1.08
    POSITIVE LOGITS
     of
    1.77
    ),
    1.31
    loxy
    1.20
    閉じ
    1.19
    但她
    1.16
    遑
    1.16
     etc
    1.15
     elegant
    1.14
     magnificent
    1.14
    NO
    1.13
    Activations Density 0.064%

    No Known Activations