© 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. 212804
    Prev
    Next
    INDEX
    Explanations

    prophet, shot, notes, liable, son

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

    offer companionship, shadow darted

    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
     ductile
    0.52
     propone
    0.48
     carbonate
    0.47
    ′-
    0.47
    สำเร็จ
    0.47
     Vương
    0.46
     phun
    0.46
     pince
    0.46
     escalera
    0.45
     Hoyt
    0.45
    POSITIVE LOGITS
    s
    0.53
    naj
    0.51
    nus
    0.49
    nosis
    0.47
    n
    0.47
    kij
    0.46
    瀆
    0.46
    nerv
    0.44
    margins
    0.44
    nos
    0.44
    Activations Density 0.001%

    No Known Activations