© 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. 202621
    Prev
    Next
    INDEX
    Explanations

    company's financial, graphics department, previously operated, November we

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

    click on the highest variance

    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
    队长
    0.55
    书记
    0.53
     kapit
    0.53
    ্লিকেশন
    0.52
    LockButton
    0.51
    疆
    0.51
     تبدی
    0.50
    university
    0.50
    领导
    0.50
    惆
    0.49
    POSITIVE LOGITS
     whatnot
    0.47
     paucity
    0.42
     regime
    0.42
     reconstit
    0.42
     domestically
    0.41
     Shreve
    0.40
     legislation
    0.39
     restructure
    0.39
     régimen
    0.39
     sheltered
    0.38
    Activations Density 0.000%

    No Known Activations