© 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. 159685
    Prev
    Next
    INDEX
    Explanations

    temporal markers

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

    thinking, critical thinking, joins

    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
    4
    0.55
    Love
    0.53
    8
    0.52
    9
    0.50
    B
    0.50
    For
    0.50
    6
    0.48
    Tr
    0.48
     трево
    0.48
     LOVE
    0.47
    POSITIVE LOGITS
     найбільш
    0.50
     namani
    0.49
     campe
    0.47
    ဣ
    0.46
    を用いて
    0.45
     fasilitas
    0.45
    इंड
    0.44
     pavatt
    0.44
     hauptsächlich
    0.44
    ヒル
    0.44
    Activations Density 0.001%

    No Known Activations