© 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. 135423
    Prev
    Next
    INDEX
    Explanations

    what questions followed by pronouns

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

    happened explains current events or past events

    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
     ఉప
    0.47
     tort
    0.46
    Claims
    0.45
     নত
    0.45
    㕕
    0.45
     ጥቅ
    0.45
    tort
    0.44
     తు
    0.44
     سلا
    0.44
     పేర్కొ
    0.43
    POSITIVE LOGITS
    י
    0.50
    atak
    0.48
    IN
    0.46
    ত
    0.46
    INH
    0.44
    也
    0.44
    킷
    0.44
    となる
    0.42
    etermin
    0.42
     problema
    0.42
    Activations Density 0.000%

    No Known Activations