© 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. 18074
    Prev
    Next
    INDEX
    Explanations

    LED, Coal, Live, flickering

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

    multilingual words

    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
    minimize
    0.41
    checklist
    0.39
    target
    0.37
     minimizes
    0.37
    protect
    0.36
    兩
    0.36
    categories
    0.35
    НО
    0.35
    compliance
    0.35
    。
    0.35
    POSITIVE LOGITS
     människor
    0.40
     آینده
    0.39
     iemand
    0.38
     quelqu
    0.38
     एखा
    0.38
     ungdom
    0.38
     kunna
    0.37
     Bollywood
    0.37
     একটা
    0.35
     bedrijven
    0.35
    Activations Density 0.000%

    No Known Activations