© 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-16K
    7. 13001
    Prev
    Next
    INDEX
    Explanations

    "verily i say unto you"

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

    code structure and function arguments

    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_16k_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
    опера
    0.47
    ниця
    0.45
    OPA
    0.45
    ادر
    0.44
    寳
    0.44
    োলার
    0.44
    தாய
    0.43
    য়াল
    0.43
    ける
    0.42
    ла
    0.42
    POSITIVE LOGITS
     Wol
    0.47
     अन्
    0.46
     찍
    0.46
     Brake
    0.45
    ordnet
    0.44
     संचार
    0.44
     deles
    0.44
     साल
    0.42
     perif
    0.42
     Slightly
    0.42
    Activations Density 0.002%

    No Known Activations