© 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. 183447
    Prev
    Next
    INDEX
    Explanations

    pluripotent Dirichlet chromatography sintering

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

    binary logic and programming constructs

    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
    聋
    0.49
    兒子
    0.49
    ليزية
    0.46
     వె
    0.46
    довать
    0.45
    Swami
    0.45
     Rumble
    0.45
    对面
    0.44
    ylvan
    0.44
    )}+\
    0.44
    POSITIVE LOGITS
     pluripotent
    0.51
     insofar
    0.50
     peint
    0.48
     juxt
    0.48
     ked
    0.47
     chromatography
    0.47
     cathe
    0.46
     Dirichlet
    0.46
    utako
    0.46
     sintering
    0.46
    Activations Density 0.001%

    No Known Activations