© 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. 164290
    Prev
    Next
    INDEX
    Explanations

    liter bottles, transmitted to, cotton to

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

    technical, explicit, and abstract concepts

    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
    lasting
    0.44
     stemming
    0.43
     女
    0.42
    ǰ
    0.42
     KUR
    0.41
    俆
    0.40
     voed
    0.40
     spot
    0.39
     بالك
    0.39
    ytuc
    0.39
    POSITIVE LOGITS
    {
    0.61
    盉
    0.56
     Ваши
    0.55
    私たち
    0.52
    私たちの
    0.51
     Анастасия
    0.50
     .+
    0.49
    이
    0.48
     этом
    0.48
     vasculature
    0.48
    Activations Density 0.000%

    No Known Activations