© 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. 189016
    Prev
    Next
    INDEX
    Explanations

    helpful words

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

    utilitarian efficiency and survival

    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
    P
    0.54
    G
    0.53
    N
    0.51
     Mas
    0.50
    Mas
    0.49
    \\
    0.48
    V
    0.48
    kinson
    0.47
    Arithmetic
    0.46
    Y
    0.46
    POSITIVE LOGITS
     shells
    0.49
    셸
    0.48
    یک
    0.47
    쉘
    0.46
     seashell
    0.46
     雷
    0.46
     법칙
    0.46
     légales
    0.45
    ່ງ
    0.45
     seashells
    0.44
    Activations Density 0.001%

    No Known Activations