© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 121115
    Prev
    Next
    INDEX
    Explanations

    betting, subscription, learning, Luke, upgrade

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

    headings before descriptions

    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
     samot
    0.50
    Results
    0.48
     t
    0.47
    ו
    0.47
    所有的
    0.46
    Figs
    0.45
    M
    0.44
    Configs
    0.43
    Manage
    0.43
     Uruguay
    0.43
    POSITIVE LOGITS
     ακόμα
    0.50
     कर्क
    0.49
    ều
    0.49
     όχι
    0.49
    famous
    0.47
    uleux
    0.46
    ập
    0.46
     সমৃদ্ধ
    0.45
    熄
    0.45
     constructed
    0.45
    Activations Density 0.001%

    No Known Activations