© 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. 117428
    Prev
    Next
    INDEX
    Explanations

    adopted a draft law

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

    conversations following explanations

    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
     Wochen
    0.48
    ৩৭
    0.48
    CCCCC
    0.46
     LongNumber
    0.46
    ৩৯
    0.45
     QuantityOnHand
    0.45
     Rhein
    0.44
    𝐊
    0.44
    ວກ
    0.44
    WeekDates
    0.44
    POSITIVE LOGITS
    知識
    0.52
    હુ
    0.50
    å
    0.50
    深い
    0.50
    知识
    0.49
    uh
    0.48
    op
    0.46
    ena
    0.46
    ik
    0.46
     sentence
    0.45
    Activations Density 0.002%

    No Known Activations