© 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. 15343
    Prev
    Next
    INDEX
    Explanations

    time to get away

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

    display segment

    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
    on
    0.57
    :
    0.55
    mau
    0.52
    то
    0.51
    s
    0.51
    mons
    0.51
     Partie
    0.50
     Lí
    0.50
    tf
    0.49
    :*
    0.49
    POSITIVE LOGITS
     ringan
    0.50
    绮
    0.47
    发展
    0.46
     stabil
    0.45
    িশীল
    0.44
    更新
    0.44
    販売
    0.43
    钵
    0.43
     booklets
    0.42
    རྒྱ
    0.42
    Activations Density 0.000%

    No Known Activations