© 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. 0
    Prev
    Next
    INDEX
    Explanations

    this approach or circumstance

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

    demonstratives and articles

    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
     ۴
    0.39
     아주
    0.37
     នៅ
    0.37
    4
    0.37
     krishna
    0.37
     steve
    0.36
     أو
    0.36
     usi
    0.36
     portug
    0.36
     غ
    0.35
    POSITIVE LOGITS
    这样做
    0.55
    這樣子
    0.47
     newfound
    0.46
    如此
    0.40
     findings
    0.39
     deliberations
    0.38
    這樣的
    0.37
     statements
    0.37
     Findings
    0.37
    த்தகைய
    0.37
    Activations Density 0.209%

    No Known Activations