© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8679
    Prev
    Next
    INDEX
    Explanations

    U.S. Patent numbers

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

    locations and regions

    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_40_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
    𝙛
    0.41
    𝗴
    0.39
    дия
    0.38
    Jf
    0.37
    АН
    0.37
    maan
    0.36
    غان
    0.35
     жа
    0.35
    сен
    0.34
     креди
    0.34
    POSITIVE LOGITS
     collapsing
    0.51
     relativistic
    0.46
    წიფ
    0.43
     ம
    0.43
     nonthermal
    0.42
     trung
    0.41
     collapse
    0.41
    ogeneities
    0.41
     nonlocal
    0.40
     analges
    0.40
    Activations Density 0.013%

    No Known Activations