© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13356
    Prev
    Next
    INDEX
    Explanations

    energy released

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

    mathematical formulas and definitions

    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_16k_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
     காலம்
    0.44
     Analyses
    0.41
     nº
    0.41
     पीड़ितों
    0.41
     SCIENCES
    0.40
     फाउंडेशन
    0.39
    髒
    0.39
    タイプの
    0.39
     медици
    0.38
     рода
    0.38
    POSITIVE LOGITS
    μέ
    0.48
    াবল
    0.44
    ل
    0.43
     pointA
    0.42
    трибу
    0.40
    জয়
    0.39
     bumper
    0.39
    боро
    0.38
    দ্ভুত
    0.38
     সাইফুদ্দিন
    0.38
    Activations Density 0.000%

    No Known Activations