© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7695
    Prev
    Next
    INDEX
    Explanations

    nature sounds and sensations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
    に関して
    2.03
    Pessoal
    1.91
    viamente
    1.87
    usakan
    1.86
    に関しては
    1.85
     (__
    1.84
     제외
    1.83
    があるので
    1.81
    +)$
    1.80
     kısm
    1.76
    POSITIVE LOGITS
    畔
    1.71
     enchanting
    1.69
     nourish
    1.65
     serene
    1.62
     nourishing
    1.62
     timeless
    1.57
     ensinar
    1.56
     adorn
    1.54
     inspire
    1.54
     fecund
    1.54
    Activations Density 0.168%

    No Known Activations