© 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. 197887
    Prev
    Next
    INDEX
    Explanations

    RTS style

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

    if, sometimes, just, wanted, seeing

    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
     에너지
    0.52
     Пав
    0.47
     объекты
    0.47
    メートル
    0.46
    𝗨
    0.46
    سور
    0.46
     لکھ
    0.45
    𝑈
    0.45
     سور
    0.45
     சுர
    0.44
    POSITIVE LOGITS
    :
    0.53
    2
    0.52
    in
    0.52
    er
    0.52
    ."
    0.52
    ig
    0.51
    ers
    0.51
    ity
    0.51
    0
    0.51
    ive
    0.50
    Activations Density 0.000%

    No Known Activations