© 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. 67631
    Prev
    Next
    INDEX
    Explanations

    common phrases

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

    events, idea, give, average, process, data

    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
    through
    0.42
     devoting
    0.40
     vattati
    0.39
     шриф
    0.39
    и
    0.38
    closeup
    0.38
    可以将
    0.38
     சுமார்
    0.38
     संधि
    0.38
    祠
    0.38
    POSITIVE LOGITS
     tut
    0.44
     komm
    0.44
     stress
    0.43
    ่ม
    0.43
     bagel
    0.41
     hora
    0.41
    رير
    0.41
     Aktual
    0.41
    ريكا
    0.40
     mach
    0.40
    Activations Density 0.000%

    No Known Activations