© 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. 188035
    Prev
    Next
    INDEX
    Explanations

    CT, Connecticut, place names

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

    non-coding RNA, controversial, movement, feeling

    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
    saver
    0.46
    વા
    0.43
     boomerang
    0.43
     affaire
    0.43
    frau
    0.43
     SA
    0.43
     UUID
    0.42
    f
    0.42
    saving
    0.42
     వర
    0.42
    POSITIVE LOGITS
    jež
    0.51
     јед
    0.51
    áte
    0.50
     खड़े
    0.50
     hMut
    0.48
    udir
    0.47
    ạt
    0.46
    avlj
    0.46
    umos
    0.46
    
    0.46
    Activations Density 0.001%

    No Known Activations