© 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. 65275
    Prev
    Next
    INDEX
    Explanations

    explaining reasons or concessions

    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
     Poincar
    -1.11
    Якщо
    -1.10
    )="
    -1.08
    今朝
    -1.04
    heater
    -1.04
    今日も
    -1.04
    InitStruct
    -1.03
    鬟
    -1.03
    */
    -1.02
    Когда
    -1.01
    POSITIVE LOGITS
     its
    1.58
     recent
    1.56
     it
    1.47
     recently
    1.46
     already
    1.46
     previous
    1.26
     previously
    1.24
     since
    1.20
     currently
    1.19
     известно
    1.13
    Activations Density 0.032%

    No Known Activations