© 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. 19245
    Prev
    Next
    INDEX
    Explanations

    up and down movement

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

    getting up and leaving

    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
     specific
    0.45
     chun
    0.43
     SBOM
    0.41
    ))^{
    0.41
     spezif
    0.41
     chant
    0.40
     اذ
    0.40
    SPEC
    0.38
    資産
    0.38
    駕
    0.38
    POSITIVE LOGITS
     keluar
    0.56
     বেরিয়ে
    0.55
     выйти
    0.54
     выход
    0.53
    出门
    0.52
     Exit
    0.51
     வெளியே
    0.51
     выхода
    0.51
    走出
    0.50
    离开了
    0.50
    Activations Density 0.046%

    No Known Activations