© 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. 156105
    Prev
    Next
    INDEX
    Explanations

    phrasal verbs and idiomatic sequences

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

    suddenly take, called, Quando si

    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
    iod
    0.50
    indari
    0.49
    p
    0.48
     destiny
    0.48
     $+
    0.47
     (+
    0.47
     เริ่ม
    0.45
    ain
    0.44
     บุ
    0.44
    re
    0.43
    POSITIVE LOGITS
    Milk
    0.55
    虺
    0.50
    Through
    0.50
    鋈
    0.50
    Doctors
    0.49
    厰
    0.49
    σμ
    0.48
    ᱝ
    0.48
    欱
    0.48
    Reasoner
    0.48
    Activations Density 0.000%

    No Known Activations