© 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. 233891
    Prev
    Next
    INDEX
    Explanations

    soil evaluation

    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
     фаразлау
    0.50
     conveys
    0.48
    ')->
    0.46
     rockers
    0.46
     accret
    0.45
     infringing
    0.45
    vesti
    0.44
     ,
    0.44
    вес
    0.44
     infringed
    0.44
    POSITIVE LOGITS
    ลา
    0.46
     Azul
    0.46
     Ferr
    0.45
    𝐿
    0.44
    𝑘
    0.44
     Jared
    0.43
    Hann
    0.43
    讚
    0.43
    鐧
    0.43
    ंसद
    0.43
    Activations Density 0.001%

    No Known Activations