© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44164
    Prev
    Next
    INDEX
    Explanations

    when, analytical, algorithm, sensors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שלנו
    0.43
    잊
    0.40
     joie
    0.39
     ಸಾವ
    0.39
    heal
    0.39
     homelessness
    0.38
     nighttime
    0.38
    停留
    0.38
     風
    0.38
     आराम
    0.38
    POSITIVE LOGITS
     když
    0.54
     وقتی
    0.50
     cuando
    0.49
     quando
    0.49
     ersten
    0.45
     ketika
    0.43
     inteligente
    0.43
     ahorita
    0.42
     kiedy
    0.41
     όταν
    0.41
    Activations Density 0.007%

    No Known Activations