© 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. 105641
    Prev
    Next
    INDEX
    Explanations

    youth question, couple years, local governments

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

    conversations and assumptions

    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
    นี้
    0.52
     you
    0.50
    ได้
    0.48
    we
    0.48
    my
    0.48
    :
    0.47
     guest
    0.47
     feuille
    0.47
    λεί
    0.46
     lagging
    0.46
    POSITIVE LOGITS
    铁路
    0.45
     парк
    0.44
    甚至是
    0.43
    قتل
    0.42
    塘
    0.42
    ريس
    0.42
    걸
    0.41
     парт
    0.41
    屶
    0.41
    oreille
    0.40
    Activations Density 0.000%

    No Known Activations