© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79281
    Prev
    Next
    INDEX
    Explanations

    noise footprint

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

    air compression and expansion

    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_31_width_262k_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
    死了
    0.44
    传送
    0.43
    在这
    0.41
     død
    0.41
     सड़
    0.41
    进行
    0.40
     fungal
    0.40
    张
    0.39
    识
    0.38
    蒋
    0.38
    POSITIVE LOGITS
     cater
    0.48
     hikers
    0.46
    compass
    0.46
    compress
    0.45
     onshore
    0.44
     compress
    0.43
    圧縮
    0.43
     horsepower
    0.43
     supercar
    0.43
    Temporary
    0.43
    Activations Density 0.016%

    No Known Activations