© 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. 34420
    Prev
    Next
    INDEX
    Explanations

    choosing or deciding

    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
    샹
    -1.01
    asantry
    -0.98
    त्तर
    -0.96
    頃は
    -0.93
    你自己
    -0.92
    यार
    -0.91
    anything
    -0.91
    ScreenState
    -0.90
    nehå
    -0.88
     nẵng
    -0.88
    POSITIVE LOGITS
     choosing
    1.55
     choose
    1.38
    Choosing
    1.32
     chooses
    1.29
     chose
    1.27
    选择
    1.20
     selecting
    1.18
    選擇
    1.17
     choice
    1.14
     changing
    1.14
    Activations Density 0.142%

    No Known Activations