© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11045
    Prev
    Next
    INDEX
    Explanations

    imagining scenarios

    np_acts-logits-general · gemini-2.5-flash-lite

    imagining examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suspiciously
    0.47
    似乎
    0.47
     WHY
    0.41
     вроде
    0.40
    ística
    0.39
     ஏன்
    0.39
    之所以
    0.39
     왜
    0.39
     Warum
    0.39
     почему
    0.38
    POSITIVE LOGITS
     imagine
    3.31
     Imagine
    3.06
    imagine
    3.06
    Imagine
    3.05
     imagines
    2.42
    想象
    2.33
    想像
    2.31
     imagina
    2.31
     imagined
    2.23
     imagining
    2.20
    Activations Density 0.254%

    No Known Activations