© 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. 127821
    Prev
    Next
    INDEX
    Explanations

    interrogative is

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

    Is there a question

    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
    \
    0.71
    ?
    0.66
    其他
    0.58
    *
    0.58
    ?..
    0.58
    (
    0.56
    你
    0.55
    ?\
    0.55
    ти
    0.54
    م
    0.52
    POSITIVE LOGITS
     acesta
    0.59
     これは
    0.58
    RAEL
    0.58
     féidir
    0.55
    chemia
    0.54
     anagram
    0.54
    ograd
    0.52
     এটি
    0.52
     a
    0.50
     caderno
    0.50
    Activations Density 0.063%

    No Known Activations