© 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. 158995
    Prev
    Next
    INDEX
    Explanations

    results of

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

    questions about why

    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
     longe
    0.49
    clustering
    0.48
     scintillation
    0.44
    в
    0.43
    í
    0.43
    เง
    0.43
    несе
    0.42
    %.
    0.42
    ∑</
    0.42
    க்த
    0.41
    POSITIVE LOGITS
     পোশাক
    0.50
    រួ
    0.50
     bridges
    0.46
     就是
    0.45
    لوار
    0.45
    সই
    0.45
    BAC
    0.44
    🍁
    0.43
     آماده
    0.43
    两个
    0.43
    Activations Density 0.001%

    No Known Activations