© 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. 149074
    Prev
    Next
    INDEX
    Explanations

    sublimation process

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

    contract binding or sexual dynamics

    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
     atualmente
    0.57
    专
    0.51
    HARAD
    0.50
    專
    0.50
    אן
    0.49
    בש
    0.49
    Ahora
    0.49
    พร
    0.49
    Established
    0.49
    안
    0.48
    POSITIVE LOGITS
     steril
    0.49
     sterile
    0.48
    ot
    0.47
     Mont
    0.47
    gettags
    0.47
    (
    0.47
    o
    0.47
     cocktails
    0.46
     by
    0.46
     Ryanair
    0.45
    Activations Density 0.000%

    No Known Activations