© 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. 1428
    Prev
    Next
    INDEX
    Explanations

    or followed by alternatives

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

    the word "even"

    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
     sechs
    0.19
     następnie
    0.18
     trzy
    0.18
     három
    0.18
     tujuh
    0.18
     двумя
    0.17
     dvě
    0.17
    ￫
    0.17
     सात
    0.17
     ثلاثة
    0.17
    POSITIVE LOGITS
     даже
    0.47
     навіть
    0.47
     even
    0.44
     thậm
    0.42
     zelfs
    0.42
    甚至是
    0.41
    even
    0.41
     حتی
    0.40
    甚至
    0.39
     bahkan
    0.39
    Activations Density 0.776%

    No Known Activations