© 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. 212707
    Prev
    Next
    INDEX
    Explanations

    bath linens

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

    Bacterial pneumonia vibe leveraging services

    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
    o
    0.64
    r
    0.63
    ai
    0.58
    t
    0.57
    ill
    0.56
    el
    0.55
    l
    0.55
    n
    0.54
    ay
    0.54
    R
    0.49
    POSITIVE LOGITS
     prévoir
    0.50
     передба
    0.49
     Override
    0.46
     பரிந்து
    0.46
    后悔
    0.46
     fortement
    0.45
     чрез
    0.44
     Excessive
    0.43
    大战
    0.43
     uzn
    0.42
    Activations Density 0.001%

    No Known Activations